{"generated_at":"2026-08-14T12:57:07Z","release_id":"c44af57d-9091-45c8-9299-96dee423e175","runs":[{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"43ece56a-4d7d-4ed0-a4dc-e8326bd11ed2","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:27:13.585026Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"0250b3b7-9d4f-518d-b490-fb0acd4945a0","score_usage_ref":"fmb-live-runs-fsa.json#43ece56a-4d7d-4ed0-a4dc-e8326bd11ed2","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-26T09:26:09.753159Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.8 Max","qwen/qwen3.8-max","qwen3.8-max"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"daf55664-0f64-5efd-82e3-07e31557aa5d","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-14T11:59:01.027623Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"3"},{"name":"max_concurrency","value":"3"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.8-max","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-c77efa5c3bd8fcd155b544e09e1a057bd04d9a5b173c3eba118f5830e4d4ef60","display_name":"Qwen3.8 Max","execution_status":"completed","model_key":"qwen/qwen3.8-max","provider_label":"Alibaba","ranking_state":"current","requested_model_id":"qwen/qwen3.8-max","revision_state":"original","run_id":"02a6a4e8-9ba2-53a7-a5c1-f458ed6e9c64","score_usage_ref":"fmb-live-runs-capstone.json#daf55664-0f64-5efd-82e3-07e31557aa5d","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"2459535f-f982-5826-81ed-c8f6d1514773","started_at":"2026-08-14T10:40:32.404045Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Sol","OpenAI: GPT-5.6 Sol","gpt-5.6-sol","openai/gpt-5.6-sol"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"44ecb470-2336-5484-bb73-e806fccd3191","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:37:48.640701Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"262144"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/eu","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-sol","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-1be2d653ab2300292f5b0a350d2b4b1f7b23fe65c0bdac75e8d7ed57a90245d1","display_name":"GPT-5.6 Sol","execution_status":"completed","model_key":"openai/gpt-5.6-sol","provider_label":"Azure EU","ranking_state":"current","requested_model_id":"openai/gpt-5.6-sol","revision_state":"original","run_id":"034d3b94-79fa-5253-b8a2-325b00aef558","score_usage_ref":"fmb-live-runs-ifrs.json#44ecb470-2336-5484-bb73-e806fccd3191","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-08-07T08:06:48.181926Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"a66a31b1-aa46-4fb9-bac6-aba8f14a3bec","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T11:51:35.345435Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-db59219469087a896c64c44340211eab8d84a80fc4709262716e98e955921b3c","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"041d3712-96eb-5cc4-8646-492f5e88ec41","score_usage_ref":"fmb-live-runs-ifrs.json#a66a31b1-aa46-4fb9-bac6-aba8f14a3bec","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-17T11:47:10.415882Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Fable 5","anthropic/claude-fable-5","claude-fable-5"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"93161fb6-3660-5778-b4b8-3e18f218c851","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:44:29.520954Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/amazon-bedrock/claude-on-aws","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-fable-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-922917b6905f7784c979ad666139c7619bc3f102210186ca640c6a3565cd65c0","display_name":"Claude Fable 5","execution_status":"completed","model_key":"anthropic/claude-fable-5","provider_label":"Amazon Bedrock","ranking_state":"current","requested_model_id":"anthropic/claude-fable-5","revision_state":"original","run_id":"047b0198-5271-5c05-80b7-fa06541ae5db","score_usage_ref":"fmb-live-runs-fin-val.json#93161fb6-3660-5778-b4b8-3e18f218c851","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-08-07T08:09:54.863656Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"2f69a0d3-33d7-4fb8-8d90-37e13c1d5bab","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T11:25:51.227453Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-c85fbc69852728714db01ed690c90b60100854c267f1a3ab041ed4d9963338b6","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"06c29e2f-4f6b-589f-9302-d0db21c300b3","score_usage_ref":"fmb-live-runs-fsa.json#2f69a0d3-33d7-4fb8-8d90-37e13c1d5bab","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T11:18:02.20288Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"ea877e06-fc11-4f1a-9764-e53856b52592","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:26:08.286715Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"07717d89-6b20-5a54-8688-82826834baea","score_usage_ref":"fmb-live-runs-fin-ma.json#ea877e06-fc11-4f1a-9764-e53856b52592","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-26T09:25:03.484141Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"4403736a-db7d-41c2-a9ce-bdcd0fd11825","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:41:50.10792Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-33afd6f7c19a6420fc5243f0a41724e1ffa8e592550a5a37370f82217589a27f","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"08b72c2d-b959-51cd-a15e-754acab87600","score_usage_ref":"fmb-live-runs-hgb.json#4403736a-db7d-41c2-a9ce-bdcd0fd11825","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-17T10:40:17.543085Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"0716240d-b1f1-4248-a2ef-1a39b6066691","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:37:37.377606Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-782fb79167e127248a0eb252629f33ffc38f450b2a06d8d237848fe302658a26","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"0a39cedd-864a-52e3-ae5f-7d05cc94df85","score_usage_ref":"fmb-live-runs-hgb.json#0716240d-b1f1-4248-a2ef-1a39b6066691","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-17T10:35:07.966088Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"867b616e-b359-48ac-92c9-5f76b517bce7","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T10:39:00.873693Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"0b6c946a-8041-5d15-832a-a5c437f7e247","score_usage_ref":"fmb-live-runs-fsa.json#867b616e-b359-48ac-92c9-5f76b517bce7","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-26T10:33:48.274061Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"fb171722-167b-4717-a0a0-888986decabe","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:49:53.131361Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-33afd6f7c19a6420fc5243f0a41724e1ffa8e592550a5a37370f82217589a27f","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"0bb64e97-5d3a-524a-9b8b-c1a0d74a8299","score_usage_ref":"fmb-live-runs-ifrs.json#fb171722-167b-4717-a0a0-888986decabe","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-17T10:44:03.099099Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"75635ecf-f5ef-44b1-8e16-75134892e8e3","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T15:07:52.759906Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-a0c68f7f84ffca1ee070a2764e139f292916c262fd09f823dfd78aa8296dd877","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"0dc9d448-1e77-5f2e-8ca9-ddb08016639f","score_usage_ref":"fmb-live-runs-fin-ma.json#75635ecf-f5ef-44b1-8e16-75134892e8e3","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T14:48:23.66455Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"50172fe9-380a-4d7a-a41a-404a9960d69b","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-16T09:56:40.122404Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v5","tool_access":"none"},"configuration_key":"config-d393fc20fd34f87c43fa7694a01bbf3d0af5f3909fd7e2b4c987e63e236e8d2b","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"0ed15428-416d-5ee1-ad37-09f42ebda6da","score_usage_ref":"fmb-live-runs.json#50172fe9-380a-4d7a-a41a-404a9960d69b","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-16T09:39:19.186274Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"9fd9f05c-f5a3-4a8f-b9d2-47dd0f424549","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:52:35.562346Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-33afd6f7c19a6420fc5243f0a41724e1ffa8e592550a5a37370f82217589a27f","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"107ad855-057f-5329-8366-0cfb24e295d3","score_usage_ref":"fmb-live-runs-fsa.json#9fd9f05c-f5a3-4a8f-b9d2-47dd0f424549","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T10:51:40.451577Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"fd42f19f-edf8-424f-a0cb-5babc4662cc1","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T13:19:03.807487Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/us-east-2","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-42ef5257ae90b31f1e29fd6d06e548ddbe9bfa4d3ccc60ad4e456187cda14055","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure US East","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"11bd3a17-1ad5-5a64-8ef1-41e763577a82","score_usage_ref":"fmb-live-runs-fin-wacc.json#fd42f19f-edf8-424f-a0cb-5babc4662cc1","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T13:04:25.896892Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"7b550565-0dba-474f-ba28-0514f7392b6a","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:55:08.447347Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-4a58c9ad7c51e53df719558cfb405c4d4e384c6467ca475bf906faea4f4a4d6b","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Together AI","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"1462120c-69e4-551e-a8eb-fe15f4920f6b","score_usage_ref":"fmb-live-runs-fin-ma.json#7b550565-0dba-474f-ba28-0514f7392b6a","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T12:52:35.937885Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"597656e2-a55e-5b79-b457-cd576849401f","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T06:42:51.144214Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"158a7e35-fff9-5eb7-afb7-b36cdfc5ed4b","score_usage_ref":"fmb-live-runs.json#597656e2-a55e-5b79-b457-cd576849401f","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-27T06:33:06.718458Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"9077d5b6-578b-438d-9eff-7b9277b53958","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:52:04.351211Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"1719ced0-e2ce-5fdb-8387-ead634916257","score_usage_ref":"fmb-live-runs-fin-wacc.json#9077d5b6-578b-438d-9eff-7b9277b53958","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-25T18:50:31.369837Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.6 Flash","gemini-3.6-flash","google/gemini-3.6-flash"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"c2f927b9-304d-572e-a71c-e1ce3f7ee31d","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T10:07:56.863231Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/google-ai-studio","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.6-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cca7ac27b204ad734de7853d84e62833ab8a4387bf5c22feb38947dd15218f84","display_name":"Gemini 3.6 Flash","execution_status":"completed","model_key":"google/gemini-3.6-flash","provider_label":"Google AI Studio","ranking_state":"current","requested_model_id":"google/gemini-3.6-flash","revision_state":"original","run_id":"175ad131-6c01-50cf-be60-f1112ba2b0a9","score_usage_ref":"fmb-live-runs-hgb.json#c2f927b9-304d-572e-a71c-e1ce3f7ee31d","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-08-07T08:08:32.252272Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"9b8893e0-baf4-49ca-8c5c-8f3f6868556b","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:07:59.745406Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-62e35c0a500c7992ccb66ddf6bdb375d1cccdb320b4ffa20b918b5a4303c78d5","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"189a3de6-f23d-5650-96ea-a5d4e749027d","score_usage_ref":"fmb-live-runs-fin-ma.json#9b8893e0-baf4-49ca-8c5c-8f3f6868556b","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T11:52:54.530064Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"c0c2eaa9-e697-42d2-bb49-3cf275ac446f","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T15:51:23.724274Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-24393c158bcc48e83c42fd72fa6a71637daf639921a9b8a2636fbfff310c6e1d","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"1a1c8784-162f-5c09-b0cd-a91b2a6fdb71","score_usage_ref":"fmb-live-runs-fin-capbud.json#c0c2eaa9-e697-42d2-bb49-3cf275ac446f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-25T15:12:21.318362Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"5595b9cc-49c8-44d7-9813-8674db293fc9","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-15T21:18:02.496007Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/wafer","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v4","tool_access":"none"},"configuration_key":"config-8874de5ab381dc807f649d8d07104701674ce1d5ba01a692ce8da09a066aefe0","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Wafer","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"1d66fd8d-a6c6-5d66-a072-62706d0090a7","score_usage_ref":"fmb-live-runs.json#5595b9cc-49c8-44d7-9813-8674db293fc9","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-15T19:58:12.554963Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"2808211c-9430-4158-8a55-fd64c481cd84","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T10:03:40.612518Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-4a58c9ad7c51e53df719558cfb405c4d4e384c6467ca475bf906faea4f4a4d6b","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Together AI","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"1df98a27-a9a6-5607-a6e0-9b9d7ca8a3d1","score_usage_ref":"fmb-live-runs-fin-capbud.json#2808211c-9430-4158-8a55-fd64c481cd84","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-23T10:01:39.399866Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"319d52a2-ddee-5abe-8fe5-8ffd7124ce35","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:52:36.853695Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"212e4821-c8bd-5b19-b1a1-fe68c2ba5a7a","score_usage_ref":"fmb-live-runs-capstone.json#319d52a2-ddee-5abe-8fe5-8ffd7124ce35","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:27:42.841273Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.8 Max","qwen/qwen3.8-max","qwen3.8-max"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"2e6ce950-8924-5201-95b6-80e89f75b063","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:41:34.150934Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.8-max","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-f289f9271dda9e6e744fd27efcbc64d6947cdf8c06cf4bf9c1d1a9c9e93c3fe0","display_name":"Qwen3.8 Max","execution_status":"completed","model_key":"qwen/qwen3.8-max","provider_label":"Alibaba","ranking_state":"current","requested_model_id":"qwen/qwen3.8-max","revision_state":"original","run_id":"236691c1-e18b-5d02-8f79-44a73907d499","score_usage_ref":"fmb-live-runs-fin-val.json#2e6ce950-8924-5201-95b6-80e89f75b063","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-08-07T08:09:46.536079Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"3de63c84-ef2a-4333-9343-2d8d3cee9b54","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:00:47.124613Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-517d3144eb1628a41a1254775383691dca18f16ff1121291ed05170e7fba9407","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"2680dbd3-18e0-586b-b038-801442ee7be7","score_usage_ref":"fmb-live-runs-fin-wacc.json#3de63c84-ef2a-4333-9343-2d8d3cee9b54","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T11:57:54.901063Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"5ec303db-453d-4d9d-b4dc-ed7d78f71379","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T15:43:33.057607Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-62e35c0a500c7992ccb66ddf6bdb375d1cccdb320b4ffa20b918b5a4303c78d5","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"26a7f023-c8eb-5ec9-a6e3-43519a297c6f","score_usage_ref":"fmb-live-runs-fin-wacc.json#5ec303db-453d-4d9d-b4dc-ed7d78f71379","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T14:59:45.523005Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"17fed503-b76c-48b9-b93b-9d8af527e887","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T15:23:32.535172Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-1c910c57a5709ee2344d09135ccf6f2c2558767b819336f3253b1bbee89d50ae","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"2b9e4874-ba5b-5b0a-86b1-df513e995b1a","score_usage_ref":"fmb-live-runs-fin-capbud.json#17fed503-b76c-48b9-b93b-9d8af527e887","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-25T15:12:23.964606Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"94bdbb20-fc5e-4083-8b72-0035401fa895","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:08:42.313237Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-4a58c9ad7c51e53df719558cfb405c4d4e384c6467ca475bf906faea4f4a4d6b","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Together AI","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"2c782193-e29c-540b-8237-318eb4e497e1","score_usage_ref":"fmb-live-runs-fin-wacc.json#94bdbb20-fc5e-4083-8b72-0035401fa895","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T12:06:46.255888Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"1a3f7b17-47ee-42d3-889a-78ab32b7c2a1","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T13:01:27.232972Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-9d1f2d0f156692dc2ab06663cfd6602fed3318f3cfc171a3c447210bafaa6dd7","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"2d2adbab-22fb-5847-9080-7b4a0cfe7688","score_usage_ref":"fmb-live-runs-fin-capbud.json#1a3f7b17-47ee-42d3-889a-78ab32b7c2a1","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-23T12:53:11.745632Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"20ac1d7b-e552-46ee-b910-88631c298f66","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:38:37.376497Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-d232cb4e8278f94a8ac41cf5dc8d11517a7a18bfe988096525d0f1dc93a30907","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"2d7a379c-76be-5f44-ab37-3ba5d7c013af","score_usage_ref":"fmb-live-runs-ifrs.json#20ac1d7b-e552-46ee-b910-88631c298f66","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-17T10:35:09.389262Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"8e674599-5745-5237-9fc8-dd23d5f624e4","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:43:31.664684Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-17adec188daded8d40eef0a0bd8e119ae182634eb7762acccd5f96c02a8423c6","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"2df71d43-5183-595d-a6f7-9002a7a06988","score_usage_ref":"fmb-live-runs-capstone.json#8e674599-5745-5237-9fc8-dd23d5f624e4","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:54.118081Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"a5827a41-b455-4539-998e-3f4de9f246ee","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-16T13:35:08.45948Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-782fb79167e127248a0eb252629f33ffc38f450b2a06d8d237848fe302658a26","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"2ea95c9d-cd5f-5bb3-a842-850923900097","score_usage_ref":"fmb-live-runs.json#a5827a41-b455-4539-998e-3f4de9f246ee","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-16T13:27:53.7536Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"ffee0d2e-0715-4c0b-873b-cad44270cc02","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:54:34.577624Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"2f94450d-9dab-56e1-8122-732eed8f8631","score_usage_ref":"fmb-live-runs-fin-capbud.json#ffee0d2e-0715-4c0b-873b-cad44270cc02","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-25T18:53:15.515213Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"c5f9dc7e-c31c-44ef-bbce-e6eb1c4775d0","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-16T06:40:51.135751Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v4","tool_access":"none"},"configuration_key":"config-a5640a517f74f5215c60166d203ddb0defd169cc6908c9fb8c3a495ec7182784","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"30e5711c-94ae-56f8-bd66-a5fa484b2fd4","score_usage_ref":"fmb-live-runs.json#c5f9dc7e-c31c-44ef-bbce-e6eb1c4775d0","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-16T06:15:23.081353Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.6 Flash","gemini-3.6-flash","google/gemini-3.6-flash"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"394ac7cd-fb38-52ce-9fc7-dc9efe7fd4c1","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T10:40:43.200765Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/google-ai-studio","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.6-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cca7ac27b204ad734de7853d84e62833ab8a4387bf5c22feb38947dd15218f84","display_name":"Gemini 3.6 Flash","execution_status":"completed","model_key":"google/gemini-3.6-flash","provider_label":"Google AI Studio","ranking_state":"current","requested_model_id":"google/gemini-3.6-flash","revision_state":"original","run_id":"31c717b8-f0ff-5951-b63d-e1e48d702155","score_usage_ref":"fmb-live-runs-fsa.json#394ac7cd-fb38-52ce-9fc7-dc9efe7fd4c1","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-08-07T10:36:33.775901Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"21b99aca-0dcc-4e40-8d23-a1432371a3fb","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T16:09:12.297268Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-62e35c0a500c7992ccb66ddf6bdb375d1cccdb320b4ffa20b918b5a4303c78d5","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"31dd288f-6993-5f64-affe-07dcea54814d","score_usage_ref":"fmb-live-runs-fin-capbud.json#21b99aca-0dcc-4e40-8d23-a1432371a3fb","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-25T15:40:29.762294Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"227557ef-c8b4-50e6-bd99-57c06f7a0b78","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:49:47.881273Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"324c2405-3746-58a5-8ea0-8d811af75652","score_usage_ref":"fmb-live-runs-capstone.json#227557ef-c8b4-50e6-bd99-57c06f7a0b78","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:27:42.841252Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"6ec6f369-c4ff-491e-ad02-46d9da02fb25","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T11:16:18.05591Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-c85fbc69852728714db01ed690c90b60100854c267f1a3ab041ed4d9963338b6","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"339f8588-18ed-5f9a-bbbc-abd783640682","score_usage_ref":"fmb-live-runs-hgb.json#6ec6f369-c4ff-491e-ad02-46d9da02fb25","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-17T10:56:50.72862Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"9425845c-b842-5371-bb56-9604a5c8ed04","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:53:54.681604Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"33e0eabc-d129-5a83-97d7-9c445b014ac2","score_usage_ref":"fmb-live-runs-capstone.json#9425845c-b842-5371-bb56-9604a5c8ed04","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:31:02.975835Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"965caa3e-1244-4271-b7e6-e0d4c570b927","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-16T13:56:27.274993Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-81589f9684b8a65f84752031b12b547d49a393bc9fc5dfcdb9ed1abdc029261f","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"37039490-7962-5f49-a2ef-c8e44d83b8a5","score_usage_ref":"fmb-live-runs.json#965caa3e-1244-4271-b7e6-e0d4c570b927","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-16T13:37:11.637909Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"47cfcf5e-5ca6-4ae3-8bfa-8766f21ad5da","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T10:20:29.838375Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"39b6aa15-49b4-587b-89ce-78c63765bf64","score_usage_ref":"fmb-live-runs-hgb.json#47cfcf5e-5ca6-4ae3-8bfa-8766f21ad5da","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-26T10:14:44.965756Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Fable 5","anthropic/claude-fable-5","claude-fable-5"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"65084126-4885-5f00-9efe-c9267f68181e","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:56:52.531319Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/amazon-bedrock/claude-on-aws","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-fable-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-922917b6905f7784c979ad666139c7619bc3f102210186ca640c6a3565cd65c0","display_name":"Claude Fable 5","execution_status":"completed","model_key":"anthropic/claude-fable-5","provider_label":"Amazon Bedrock","ranking_state":"current","requested_model_id":"anthropic/claude-fable-5","revision_state":"original","run_id":"3de96c82-d2ae-5629-963d-eb38a2d4caf3","score_usage_ref":"fmb-live-runs-fin-capbud.json#65084126-4885-5f00-9efe-c9267f68181e","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-08-07T08:07:25.264553Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"bc0f651c-742f-4c05-bc0f-1f3fe7efcea8","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T10:32:56.924164Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"3e230af7-aa17-5953-bcaf-20cec0ccbe1c","score_usage_ref":"fmb-live-runs-ifrs.json#bc0f651c-742f-4c05-bc0f-1f3fe7efcea8","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-26T10:20:31.099373Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"724a3998-0e06-5bfd-a566-21873d55bb99","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T06:41:09.443988Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"4141bff2-8b92-507e-954d-9c173bcaa047","score_usage_ref":"fmb-live-runs.json#724a3998-0e06-5bfd-a566-21873d55bb99","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-27T06:33:04.771019Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"0a0176ca-8158-41a9-99df-9a31c3ef7c31","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-18T22:01:58.928922Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-e655d27b15f277dc1755feacaff749ccea423e9db3ceb7b66c3d556d39c9ca0f","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"41fd5c4a-ad1d-58a0-a72b-163265c413e9","score_usage_ref":"fmb-live-runs.json#0a0176ca-8158-41a9-99df-9a31c3ef7c31","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-18T21:00:24.304314Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"9a84a2d3-9e3f-4906-9d4c-bd0759d5ccd5","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T11:50:59.210232Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-ef35aa140459d269d244a80213bd2ef39df837b9119cedcba3ff57f968259dd0","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"4891bc8d-693c-531e-a1ae-0702a3a621cc","score_usage_ref":"fmb-live-runs-fin-wacc.json#9a84a2d3-9e3f-4906-9d4c-bd0759d5ccd5","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T10:05:40.288911Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"16f16b14-e315-5e40-bf9c-05c964d9f22c","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:40:09.67841Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-a61eea0bb81422c37dc8a2d17ddb7886a06977321b3191751c6bb9c18d9d9c51","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"49e08f5f-e6ea-5591-bc77-9aad5f01d4e3","score_usage_ref":"fmb-live-runs-capstone.json#16f16b14-e315-5e40-bf9c-05c964d9f22c","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:45.5553Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"ad400549-a0c9-4d0a-8a89-0b298a7aaa92","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-21T12:45:02.545171Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-a51986a6d29447ce638816e9412e0da96219b04bdcabf79142aff64fb0d7e465","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Together AI","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"4e0822d1-749e-5947-bb58-053c22987fe4","score_usage_ref":"fmb-live-runs-hgb.json#ad400549-a0c9-4d0a-8a89-0b298a7aaa92","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-21T12:36:06.476037Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"8acbd7b8-91c6-5346-8540-851cd5882d7b","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:42:39.486197Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cc67c176ea6b2dfd3786955295723e7abe2b413c7adaa05bf3fc46adee759a6a","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"4fdf615c-8de1-5a4b-af83-bf569ec12768","score_usage_ref":"fmb-live-runs-ifrs.json#8acbd7b8-91c6-5346-8540-851cd5882d7b","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-08-07T08:06:49.393254Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"882e2087-dfcf-4652-b3d0-6e2e388410d1","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T10:00:57.592374Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-517d3144eb1628a41a1254775383691dca18f16ff1121291ed05170e7fba9407","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"505e7d85-35ce-5152-9dbc-da23bfc9b7fe","score_usage_ref":"fmb-live-runs-fin-ma.json#882e2087-dfcf-4652-b3d0-6e2e388410d1","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T09:58:20.687752Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"86d7d045-5260-4ea7-a485-0020ad7764ed","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T12:03:36.651979Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-db59219469087a896c64c44340211eab8d84a80fc4709262716e98e955921b3c","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"5145fa80-bb7e-58af-82f0-13e518d86c8a","score_usage_ref":"fmb-live-runs-fsa.json#86d7d045-5260-4ea7-a485-0020ad7764ed","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T11:56:18.927371Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"30b82524-1379-4de6-b4e9-ca532959267d","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-18T21:30:42.492255Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-e655d27b15f277dc1755feacaff749ccea423e9db3ceb7b66c3d556d39c9ca0f","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"51874bd4-7ece-5434-bb99-dd6f81e32d54","score_usage_ref":"fmb-live-runs-fsa.json#30b82524-1379-4de6-b4e9-ca532959267d","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-18T21:16:35.523669Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"c392290d-1fc0-4ea5-82fc-c950f7b2c241","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T14:01:57.86348Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-a0c68f7f84ffca1ee070a2764e139f292916c262fd09f823dfd78aa8296dd877","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"520e893b-6201-5632-9241-2930dcef4d42","score_usage_ref":"fmb-live-runs-fin-wacc.json#c392290d-1fc0-4ea5-82fc-c950f7b2c241","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T13:26:55.367921Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.6 Flash","gemini-3.6-flash","google/gemini-3.6-flash"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"421a9e5e-f26a-5f30-a819-bd259b9f2f6d","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:18:04.454261Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/google-ai-studio","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.6-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cca7ac27b204ad734de7853d84e62833ab8a4387bf5c22feb38947dd15218f84","display_name":"Gemini 3.6 Flash","execution_status":"completed","model_key":"google/gemini-3.6-flash","provider_label":"Google AI Studio","ranking_state":"current","requested_model_id":"google/gemini-3.6-flash","revision_state":"original","run_id":"524965e7-2b54-5efd-b252-76377da1c8ba","score_usage_ref":"fmb-live-runs-fin-ma.json#421a9e5e-f26a-5f30-a819-bd259b9f2f6d","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-08-07T08:05:24.735394Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"e1041cd4-56d9-4a92-b0e6-d9176375ca08","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T10:10:23.736173Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-a0c68f7f84ffca1ee070a2764e139f292916c262fd09f823dfd78aa8296dd877","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"5584d036-1590-50c3-95c8-e822d5d3ea77","score_usage_ref":"fmb-live-runs-fin-capbud.json#e1041cd4-56d9-4a92-b0e6-d9176375ca08","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-23T08:50:28.124896Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"39537149-3df7-47b6-852a-20ee981fec73","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T11:03:09.521984Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-b96e71013f467814bddadef91d99806c120e4e768913d84cdeefe91453522e75","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"57d6b8a9-1f29-54b7-9af3-c43155568ea9","score_usage_ref":"fmb-live-runs-hgb.json#39537149-3df7-47b6-852a-20ee981fec73","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-17T10:59:38.340375Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"c816700e-6ee3-46fe-864c-32aec80c2b57","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:15:05.456112Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex/global","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-9a66f1bcd46b2485b74793e4a7199b6f5194797775e928fe78f31ab6bf7e5ee2","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI Global","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"58358b9d-3029-5be4-81d1-d999171af52c","score_usage_ref":"fmb-live-runs-fin-ma.json#c816700e-6ee3-46fe-864c-32aec80c2b57","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T12:12:26.855274Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"7b4b828d-a528-4a40-ab85-e28d33568da9","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T09:56:25.07793Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-9d1f2d0f156692dc2ab06663cfd6602fed3318f3cfc171a3c447210bafaa6dd7","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"5926310a-7889-5167-9ea6-1a6992e2f7d3","score_usage_ref":"fmb-live-runs-fin-wacc.json#7b4b828d-a528-4a40-ab85-e28d33568da9","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T09:53:20.804239Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"2320b5e3-d765-5ae8-86e6-3d2d8e789303","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T09:02:36.593637Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cc67c176ea6b2dfd3786955295723e7abe2b413c7adaa05bf3fc46adee759a6a","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"5a62cff2-dfe6-5b2e-b415-2a5b4661e047","score_usage_ref":"fmb-live-runs-fin-wacc.json#2320b5e3-d765-5ae8-86e6-3d2d8e789303","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-08-07T08:07:04.061514Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"5eb906b6-e5dd-4877-8dfa-8d331dfed758","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:54:34.884007Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"5a6f4b23-a5be-538c-b70e-a7d0b9983c4e","score_usage_ref":"fmb-live-runs-fin-val.json#5eb906b6-e5dd-4877-8dfa-8d331dfed758","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-25T18:53:15.48584Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"a7b9e0db-9c04-43c3-8d47-82ef60980e6d","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:48:20.234596Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"5b7a6e5e-0687-54f1-b31e-9b22f35b20d7","score_usage_ref":"fmb-live-runs-fin-capbud.json#a7b9e0db-9c04-43c3-8d47-82ef60980e6d","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-25T18:45:44.682099Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"0ea15659-ddbf-4b48-a093-6dc0e02d3d9a","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:53:21.02237Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-ac3540dedb1811b40484ac4ab9a5fa854f2caaa286beb4ab6f3f54a46f3fa288","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"5d1adc14-bb02-568a-986b-7f1826cf724b","score_usage_ref":"fmb-live-runs-ifrs.json#0ea15659-ddbf-4b48-a093-6dc0e02d3d9a","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-17T10:49:43.170603Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"282234b0-56fa-5f05-81c4-9d21905b7769","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:37:02.293818Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cc67c176ea6b2dfd3786955295723e7abe2b413c7adaa05bf3fc46adee759a6a","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"5e8e530e-33a5-5dcc-8e68-87d7b4c38d20","score_usage_ref":"fmb-live-runs-fin-val.json#282234b0-56fa-5f05-81c4-9d21905b7769","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-08-07T08:06:17.577896Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"f9239761-a2a2-4279-b802-2326e24aa04f","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:33:06.425882Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"5f90378b-e917-5c59-8bb3-8de090f3602d","score_usage_ref":"fmb-live-runs-fin-val.json#f9239761-a2a2-4279-b802-2326e24aa04f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-26T09:30:30.521947Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"88aa085c-efcf-4ec5-8d54-b635773995e6","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T13:16:01.889763Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-1c910c57a5709ee2344d09135ccf6f2c2558767b819336f3253b1bbee89d50ae","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"5fe6d112-e588-5e2a-ade2-0c58e8f6f6c0","score_usage_ref":"fmb-live-runs-fin-ma.json#88aa085c-efcf-4ec5-8d54-b635773995e6","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T13:06:59.849486Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"5995fb89-11dc-479f-8fc5-7276f40de6b0","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:04:50.701164Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex/global","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-9a66f1bcd46b2485b74793e4a7199b6f5194797775e928fe78f31ab6bf7e5ee2","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI Global","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"63c63092-5944-5631-a9c1-b4e71d943f4f","score_usage_ref":"fmb-live-runs-fin-val.json#5995fb89-11dc-479f-8fc5-7276f40de6b0","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T12:02:33.986832Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"f5515803-ef51-487e-9a24-d8ebb44a013f","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:32:00.488956Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-9d1f2d0f156692dc2ab06663cfd6602fed3318f3cfc171a3c447210bafaa6dd7","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"652b10b9-bf5a-57af-8613-fbfd060764b3","score_usage_ref":"fmb-live-runs-fin-val.json#f5515803-ef51-487e-9a24-d8ebb44a013f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T12:30:00.432878Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"e2c93c44-8c9a-422f-b9f5-475f5db27f3a","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:26:30.702539Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"655db4de-bc47-5ba3-874a-da84651823d9","score_usage_ref":"fmb-live-runs-fin-wacc.json#e2c93c44-8c9a-422f-b9f5-475f5db27f3a","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-26T09:23:19.311821Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.6 Flash","gemini-3.6-flash","google/gemini-3.6-flash"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"c1c28e28-93f3-5c5d-8b38-34af2ccca862","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-14T08:51:05.357234Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"3"},{"name":"max_concurrency","value":"3"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/google-ai-studio","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.6-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-197b943d9d0626c6e57b33209bd05f6e71e9e4c5782442245f6415e5f1a9a061","display_name":"Gemini 3.6 Flash","execution_status":"completed","model_key":"google/gemini-3.6-flash","provider_label":"Google AI Studio","ranking_state":"current","requested_model_id":"google/gemini-3.6-flash","revision_state":"original","run_id":"65f4c1ba-82df-5a30-9eda-8288a24e58ab","score_usage_ref":"fmb-live-runs-capstone.json#c1c28e28-93f3-5c5d-8b38-34af2ccca862","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"2459535f-f982-5826-81ed-c8f6d1514773","started_at":"2026-08-14T06:51:16.975277Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"13e12be2-1b52-432a-bd78-c52ad1b1362c","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T11:06:53.433454Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-b96e71013f467814bddadef91d99806c120e4e768913d84cdeefe91453522e75","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"6623b9b0-61a8-5578-9c8f-1b5ed6260c94","score_usage_ref":"fmb-live-runs-ifrs.json#13e12be2-1b52-432a-bd78-c52ad1b1362c","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-17T11:05:02.415338Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"10d3a099-1444-46d9-87a1-b553922a98bc","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:53:13.507867Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"67768592-87fa-5d40-a0cd-1448d8aef9ac","score_usage_ref":"fmb-live-runs-fsa.json#10d3a099-1444-46d9-87a1-b553922a98bc","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-25T18:52:05.342119Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"2cb7a797-ba68-4df4-a96b-f01405430267","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T09:54:08.456375Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-d232cb4e8278f94a8ac41cf5dc8d11517a7a18bfe988096525d0f1dc93a30907","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"67c6b413-52c2-5c36-b149-724922a15b33","score_usage_ref":"fmb-live-runs-fsa.json#2cb7a797-ba68-4df4-a96b-f01405430267","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T09:49:03.185708Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"150276cd-c31a-420a-8e95-fae7f058ef5e","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-21T11:32:18.011393Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-c85fbc69852728714db01ed690c90b60100854c267f1a3ab041ed4d9963338b6","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"68cbab42-6612-55b6-acc0-6acf3b26f0b5","score_usage_ref":"fmb-live-runs-ifrs.json#150276cd-c31a-420a-8e95-fae7f058ef5e","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-21T11:14:20.652439Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.8 Max","qwen/qwen3.8-max","qwen3.8-max"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"21c6cdcd-98b8-5216-8b13-472f6587faa6","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T10:01:04.249316Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.8-max","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-f289f9271dda9e6e744fd27efcbc64d6947cdf8c06cf4bf9c1d1a9c9e93c3fe0","display_name":"Qwen3.8 Max","execution_status":"completed","model_key":"qwen/qwen3.8-max","provider_label":"Alibaba","ranking_state":"current","requested_model_id":"qwen/qwen3.8-max","revision_state":"original","run_id":"6ae64100-f543-5a05-a16c-f7f163ff9724","score_usage_ref":"fmb-live-runs-hgb.json#21c6cdcd-98b8-5216-8b13-472f6587faa6","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-08-07T08:07:55.481552Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"5125be3a-8719-49a6-80ff-f92ada19eb62","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:57:06.607147Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"6c016bbb-c4cd-54c2-a31b-cbd6d4956c7d","score_usage_ref":"fmb-live-runs-ifrs.json#5125be3a-8719-49a6-80ff-f92ada19eb62","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-25T18:55:57.228364Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Fable 5","anthropic/claude-fable-5","claude-fable-5"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"e5fb6800-b674-55d7-9e8c-ba30032b565c","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T11:31:35.97591Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/amazon-bedrock/claude-on-aws","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-fable-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-922917b6905f7784c979ad666139c7619bc3f102210186ca640c6a3565cd65c0","display_name":"Claude Fable 5","execution_status":"completed","model_key":"anthropic/claude-fable-5","provider_label":"Amazon Bedrock","ranking_state":"current","requested_model_id":"anthropic/claude-fable-5","revision_state":"original","run_id":"6ea46f77-88bc-5985-8b58-7beface4b2a4","score_usage_ref":"fmb-live-runs-fsa.json#e5fb6800-b674-55d7-9e8c-ba30032b565c","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-08-07T11:27:06.628825Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"74566f95-41ff-521f-b0a5-8fea59044c7b","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-14T07:39:47.037987Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"3"},{"name":"max_concurrency","value":"3"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-b2d14de9f9b48ff5b72675844c905dffc89d278c42a8fbf59672f04bdffeb2f5","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"6f32c95b-abae-53a0-b9f1-438f8a6ddad0","score_usage_ref":"fmb-live-runs-capstone.json#74566f95-41ff-521f-b0a5-8fea59044c7b","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"2459535f-f982-5826-81ed-c8f6d1514773","started_at":"2026-08-14T06:23:06.760335Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"823eeaa4-afca-435e-8e9b-f512af82f933","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T09:45:54.506367Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex/global","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-9a66f1bcd46b2485b74793e4a7199b6f5194797775e928fe78f31ab6bf7e5ee2","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI Global","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"7182025a-4b9a-59fd-997c-e01d58a9545a","score_usage_ref":"fmb-live-runs-fin-capbud.json#823eeaa4-afca-435e-8e9b-f512af82f933","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-23T09:42:46.962358Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.6 Flash","gemini-3.6-flash","google/gemini-3.6-flash"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"08c10202-cfb9-5bfc-af29-7fabc41c4381","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:35:54.314603Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/google-ai-studio","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.6-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cca7ac27b204ad734de7853d84e62833ab8a4387bf5c22feb38947dd15218f84","display_name":"Gemini 3.6 Flash","execution_status":"completed","model_key":"google/gemini-3.6-flash","provider_label":"Google AI Studio","ranking_state":"current","requested_model_id":"google/gemini-3.6-flash","revision_state":"original","run_id":"7530349e-79d3-5838-a38a-feaac3d68314","score_usage_ref":"fmb-live-runs-ifrs.json#08c10202-cfb9-5bfc-af29-7fabc41c4381","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-08-07T08:06:40.35508Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"69696a5f-792f-4d94-8c2d-59e9a825266a","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-18T21:56:38.22831Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-e655d27b15f277dc1755feacaff749ccea423e9db3ceb7b66c3d556d39c9ca0f","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"76d7eb60-1ee5-5e68-9178-2f260311bc22","score_usage_ref":"fmb-live-runs-ifrs.json#69696a5f-792f-4d94-8c2d-59e9a825266a","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-18T21:48:03.839506Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"71460593-cb12-5fe2-9c42-4da69ce6530c","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:46:12.784518Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-789c12935fb32ba8f37e7f4d7e61ddd93ff98f90677580aeeed3d1ec7c3c7894","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"7804a721-4860-5f2b-b026-ed2d66d92529","score_usage_ref":"fmb-live-runs-capstone.json#71460593-cb12-5fe2-9c42-4da69ce6530c","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:56.785677Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Sol","OpenAI: GPT-5.6 Sol","gpt-5.6-sol","openai/gpt-5.6-sol"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"2623f8b4-486a-57ae-bbc3-65b913318de9","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T10:04:17.278161Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"262144"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/eu","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-sol","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-1be2d653ab2300292f5b0a350d2b4b1f7b23fe65c0bdac75e8d7ed57a90245d1","display_name":"GPT-5.6 Sol","execution_status":"completed","model_key":"openai/gpt-5.6-sol","provider_label":"Azure EU","ranking_state":"current","requested_model_id":"openai/gpt-5.6-sol","revision_state":"original","run_id":"79667d30-3a54-5030-88ba-2c860b89bf17","score_usage_ref":"fmb-live-runs-hgb.json#2623f8b4-486a-57ae-bbc3-65b913318de9","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-08-07T08:08:21.395547Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Sol","OpenAI: GPT-5.6 Sol","gpt-5.6-sol","openai/gpt-5.6-sol"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"ccd02ed7-f61b-57bf-a12c-74281c7914ad","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T09:06:37.119371Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"262144"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/eu","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-sol","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-1be2d653ab2300292f5b0a350d2b4b1f7b23fe65c0bdac75e8d7ed57a90245d1","display_name":"GPT-5.6 Sol","execution_status":"completed","model_key":"openai/gpt-5.6-sol","provider_label":"Azure EU","ranking_state":"current","requested_model_id":"openai/gpt-5.6-sol","revision_state":"original","run_id":"79d2225b-8728-5df4-8061-d9c149511fe4","score_usage_ref":"fmb-live-runs-fin-wacc.json#ccd02ed7-f61b-57bf-a12c-74281c7914ad","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-08-07T08:07:19.905778Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"abd01de3-5a15-4e1c-a3a5-49e9e457d725","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-16T10:57:51.313071Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v5","tool_access":"none"},"configuration_key":"config-db45eba4cc760571e4de2b3951c745eb05b9aba1db8e23a97727b99a8c3765cb","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"79e6d34b-f510-50de-92f3-9613526f0b63","score_usage_ref":"fmb-live-runs.json#abd01de3-5a15-4e1c-a3a5-49e9e457d725","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-16T10:48:47.417357Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"54ce536d-3ee1-44bb-8329-ad1062b0396d","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T13:20:48.812869Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-517d3144eb1628a41a1254775383691dca18f16ff1121291ed05170e7fba9407","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"7a3e0f30-68d5-53f1-b392-76ead4bf63b0","score_usage_ref":"fmb-live-runs-fin-capbud.json#54ce536d-3ee1-44bb-8329-ad1062b0396d","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-23T13:17:40.069864Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"76ef3c80-e2af-51d9-9822-da4a805d077b","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T09:39:16.254616Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cc67c176ea6b2dfd3786955295723e7abe2b413c7adaa05bf3fc46adee759a6a","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"7c8039e9-5a96-5831-a745-baa2b1043c49","score_usage_ref":"fmb-live-runs-fin-capbud.json#76ef3c80-e2af-51d9-9822-da4a805d077b","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-08-07T08:07:41.075012Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"a740efee-bcbe-4287-b885-4095cb381dda","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T14:28:09.952615Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-a0c68f7f84ffca1ee070a2764e139f292916c262fd09f823dfd78aa8296dd877","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"7e1a65b7-311b-51e1-9fca-fe2602b184f0","score_usage_ref":"fmb-live-runs-fin-val.json#a740efee-bcbe-4287-b885-4095cb381dda","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T14:03:38.819771Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"08e3a01c-cb9b-5154-a64d-c54cdbce73ca","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:42:40.439906Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-9978c09937f164a489f03a355ab10ecdf9b6e502f6503285a8f25fadc01b3136","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"7e4e2c9d-e2ea-54e0-8bb8-8c6116fbe0e3","score_usage_ref":"fmb-live-runs-capstone.json#08e3a01c-cb9b-5154-a64d-c54cdbce73ca","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:49.036114Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"03700801-ab9d-510f-918b-09631c7a5164","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:46:58.810048Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-a026984a6b07490c6062157850f436aef8641a483028dffd95d14bd915367935","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"7edb131b-7965-5478-8ffe-f5b8d29dc54d","score_usage_ref":"fmb-live-runs-capstone.json#03700801-ab9d-510f-918b-09631c7a5164","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:57.455699Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Fable 5","anthropic/claude-fable-5","claude-fable-5"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"213a9d84-3297-5442-868b-2ae01b344cab","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:38:27.347099Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/amazon-bedrock/claude-on-aws","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-fable-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-922917b6905f7784c979ad666139c7619bc3f102210186ca640c6a3565cd65c0","display_name":"Claude Fable 5","execution_status":"completed","model_key":"anthropic/claude-fable-5","provider_label":"Amazon Bedrock","ranking_state":"current","requested_model_id":"anthropic/claude-fable-5","revision_state":"original","run_id":"80db2876-fc59-5691-8fbd-8d0858907f32","score_usage_ref":"fmb-live-runs-ifrs.json#213a9d84-3297-5442-868b-2ae01b344cab","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-08-07T08:06:40.355229Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"4a352822-a987-4aa4-a11e-a676e1c31995","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:54:28.857897Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"81c5ffb6-1bee-5df3-ae5b-8c75c3931d76","score_usage_ref":"fmb-live-runs-fin-wacc.json#4a352822-a987-4aa4-a11e-a676e1c31995","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-25T18:53:15.498797Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"bb20db15-d7f5-46ce-a877-d741657b83bc","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-16T11:26:43.072086Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-7a07f26a7171c61f694ee8f734a7eb2c45b290ebbc0233f772221be3f41789b2","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"8381a6a6-cd35-5194-ada3-b3d01497a50a","score_usage_ref":"fmb-live-runs.json#bb20db15-d7f5-46ce-a877-d741657b83bc","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-16T11:16:27.515454Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"28ba1499-6892-4140-9eb9-f54c0387bc85","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T11:54:04.565644Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex/global","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-9a66f1bcd46b2485b74793e4a7199b6f5194797775e928fe78f31ab6bf7e5ee2","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI Global","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"83ee5c4f-0c0b-53f9-8d60-3a05fb3bd764","score_usage_ref":"fmb-live-runs-fin-wacc.json#28ba1499-6892-4140-9eb9-f54c0387bc85","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T11:51:44.612095Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"ea5ad044-40a1-5a0f-ba83-6c11a70c2d40","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-14T12:38:17.817924Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"3"},{"name":"max_concurrency","value":"3"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-b2d14de9f9b48ff5b72675844c905dffc89d278c42a8fbf59672f04bdffeb2f5","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"84074241-cdd4-5693-aa35-c51418493976","score_usage_ref":"fmb-live-runs.json#ea5ad044-40a1-5a0f-ba83-6c11a70c2d40","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"d21fb47d-f7d2-5250-bd36-e5018ec61162","started_at":"2026-08-14T12:33:14.55568Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"2f8ba2cf-8827-4f70-a331-86af7a48c6f1","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T09:04:42.409871Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-1c910c57a5709ee2344d09135ccf6f2c2558767b819336f3253b1bbee89d50ae","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"858b122b-8331-5974-bac6-78d2f7597fcd","score_usage_ref":"fmb-live-runs-fin-wacc.json#2f8ba2cf-8827-4f70-a331-86af7a48c6f1","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T08:51:21.574258Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.8 Max","qwen/qwen3.8-max","qwen3.8-max"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"8b07ed94-e207-5a42-8edf-4140eafd0d15","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:43:36.872591Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.8-max","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-f289f9271dda9e6e744fd27efcbc64d6947cdf8c06cf4bf9c1d1a9c9e93c3fe0","display_name":"Qwen3.8 Max","execution_status":"completed","model_key":"qwen/qwen3.8-max","provider_label":"Alibaba","ranking_state":"current","requested_model_id":"qwen/qwen3.8-max","revision_state":"original","run_id":"87085c40-cbab-5146-9ae4-7e49e4d13482","score_usage_ref":"fmb-live-runs-ifrs.json#8b07ed94-e207-5a42-8edf-4140eafd0d15","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-08-07T08:06:52.143117Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"222986ff-61f4-4802-953e-a64ecf939d0a","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T09:59:18.37528Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-81589f9684b8a65f84752031b12b547d49a393bc9fc5dfcdb9ed1abdc029261f","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"87a3e9ac-f0b0-55ca-bfd9-8e5d289321a8","score_usage_ref":"fmb-live-runs-hgb.json#222986ff-61f4-4802-953e-a64ecf939d0a","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-17T09:49:01.019296Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"49f269b7-86e4-4ecd-b425-45fb25f25f2f","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:55:43.011239Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"88579dc8-e1da-59e6-a40a-6efd2081066f","score_usage_ref":"fmb-live-runs-hgb.json#49f269b7-86e4-4ecd-b425-45fb25f25f2f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-25T18:54:35.730427Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"44567540-359a-465a-a7b6-a8da77532cac","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:14:52.316134Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"8963fe56-d87a-554b-9828-ee09f47f7f43","score_usage_ref":"fmb-live-runs-fin-capbud.json#44567540-359a-465a-a7b6-a8da77532cac","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-26T09:12:38.932011Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"3cf6b832-7d2a-4ec0-b49d-53c1859ca07d","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T11:56:22.707233Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-9d1f2d0f156692dc2ab06663cfd6602fed3318f3cfc171a3c447210bafaa6dd7","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"89678f61-7f98-5f76-875d-ac78f06c9e58","score_usage_ref":"fmb-live-runs-fin-ma.json#3cf6b832-7d2a-4ec0-b49d-53c1859ca07d","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T11:54:59.73725Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"c0a3ce92-6eeb-49e0-be25-de9b78eb8fee","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T13:06:00.229685Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/morph","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"minimax/minimax-m3","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-517d3144eb1628a41a1254775383691dca18f16ff1121291ed05170e7fba9407","display_name":"MiniMax M3","execution_status":"completed","model_key":"minimax/minimax-m3","provider_label":"Morph","ranking_state":"current","requested_model_id":"minimax/minimax-m3","revision_state":"original","run_id":"89facfc5-7936-5f43-8bcb-153a4bead2b1","score_usage_ref":"fmb-live-runs-fin-val.json#c0a3ce92-6eeb-49e0-be25-de9b78eb8fee","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T13:03:18.172624Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"a139f514-f098-4aa5-9870-98bc7505b1fe","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:25:02.29645Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"8b00b9f6-1b15-5dcb-86b6-0243c51d1111","score_usage_ref":"fmb-live-runs-fin-val.json#a139f514-f098-4aa5-9870-98bc7505b1fe","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-26T09:23:59.533125Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"276e4acf-4f87-4687-9aba-5260ebc7eec6","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T12:04:36.244094Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-81589f9684b8a65f84752031b12b547d49a393bc9fc5dfcdb9ed1abdc029261f","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"8b51ea77-0850-5c83-a8ca-9ad3d6d8e6fc","score_usage_ref":"fmb-live-runs-fsa.json#276e4acf-4f87-4687-9aba-5260ebc7eec6","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T11:52:49.728095Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.8 Max","qwen/qwen3.8-max","qwen3.8-max"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"eb4be6e9-25f1-578e-a96a-87a07f18f23f","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:31:44.832157Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.8-max","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-f289f9271dda9e6e744fd27efcbc64d6947cdf8c06cf4bf9c1d1a9c9e93c3fe0","display_name":"Qwen3.8 Max","execution_status":"completed","model_key":"qwen/qwen3.8-max","provider_label":"Alibaba","ranking_state":"current","requested_model_id":"qwen/qwen3.8-max","revision_state":"original","run_id":"8c49ab45-8a8e-5c8d-bac1-4fb044a3f7ea","score_usage_ref":"fmb-live-runs-fsa.json#eb4be6e9-25f1-578e-a96a-87a07f18f23f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-08-07T08:05:53.095023Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"005d2331-6b72-4c05-991b-fed12aae66f8","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T13:03:46.000756Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-ef35aa140459d269d244a80213bd2ef39df837b9119cedcba3ff57f968259dd0","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"8dd75ad7-55ba-515d-ba16-587c1b06e435","score_usage_ref":"fmb-live-runs-fin-capbud.json#005d2331-6b72-4c05-991b-fed12aae66f8","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-23T13:01:53.686623Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"29c50c3d-c8b8-468c-8934-3a206d2821cc","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:53:14.574756Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"947992ce-3600-5e5a-8922-6add618ab79e","score_usage_ref":"fmb-live-runs-hgb.json#29c50c3d-c8b8-468c-8934-3a206d2821cc","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-25T18:52:05.34854Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"ab4ab831-d982-425e-aab7-0289596a2315","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T10:08:54.049964Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"9490f957-b23f-584b-ba1a-c36babad873b","score_usage_ref":"fmb-live-runs-fin-ma.json#ab4ab831-d982-425e-aab7-0289596a2315","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-26T10:01:04.575365Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"4c3698ac-d42e-4f39-8f3d-2a476e477859","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:28:24.60174Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"95a0bb96-fc3c-50dc-a403-53d8a707799c","score_usage_ref":"fmb-live-runs-hgb.json#4c3698ac-d42e-4f39-8f3d-2a476e477859","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-26T09:27:14.818595Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"38aa8e3a-02a8-4e95-bacf-a5eeb2b5cd8f","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-16T11:53:10.333795Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-9aca6024ebc78b5e7d9bbe3600e040823fca9bad68e02d4b154acbe1230ad4b6","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"983e4710-5969-5c34-8349-2aa739d589b2","score_usage_ref":"fmb-live-runs.json#38aa8e3a-02a8-4e95-bacf-a5eeb2b5cd8f","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-16T11:44:07.40266Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"e136359f-ee10-4ea0-a819-38baeccfe248","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:46:52.702736Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-62e35c0a500c7992ccb66ddf6bdb375d1cccdb320b4ffa20b918b5a4303c78d5","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"9a339124-1499-523b-8e4e-ecd4c1aaa66d","score_usage_ref":"fmb-live-runs-fin-val.json#e136359f-ee10-4ea0-a819-38baeccfe248","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T12:08:53.5815Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"893f7459-acd2-43ee-8276-ec1f5048ac53","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T16:03:02.625046Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-24393c158bcc48e83c42fd72fa6a71637daf639921a9b8a2636fbfff310c6e1d","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"9dd8f3cd-34fe-59b1-8726-86a701bd3e34","score_usage_ref":"fmb-live-runs-fin-ma.json#893f7459-acd2-43ee-8276-ec1f5048ac53","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T15:37:43.059922Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"45faa518-0e69-4aaa-8ac6-8bf0fe4051cc","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:48:15.516083Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-ac3540dedb1811b40484ac4ab9a5fa854f2caaa286beb4ab6f3f54a46f3fa288","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"a02bc1b8-a79b-54ec-a4d7-78f1e9e9fb78","score_usage_ref":"fmb-live-runs-hgb.json#45faa518-0e69-4aaa-8ac6-8bf0fe4051cc","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-17T10:44:02.561125Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"5d89e353-30a2-5dc4-a347-e529eb3890cb","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T06:41:43.747447Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"a24a4d05-27ef-5083-91d0-96148c3a4cfe","score_usage_ref":"fmb-live-runs.json#5d89e353-30a2-5dc4-a347-e529eb3890cb","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-27T06:33:04.771021Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Sol","OpenAI: GPT-5.6 Sol","gpt-5.6-sol","openai/gpt-5.6-sol"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"efcbe08d-f92d-51bb-9b52-57999af5c107","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T09:28:28.617062Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"262144"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/eu","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-sol","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-1be2d653ab2300292f5b0a350d2b4b1f7b23fe65c0bdac75e8d7ed57a90245d1","display_name":"GPT-5.6 Sol","execution_status":"completed","model_key":"openai/gpt-5.6-sol","provider_label":"Azure EU","ranking_state":"current","requested_model_id":"openai/gpt-5.6-sol","revision_state":"original","run_id":"a26f7b0c-1aa9-5870-b460-a3d144244fea","score_usage_ref":"fmb-live-runs-fin-capbud.json#efcbe08d-f92d-51bb-9b52-57999af5c107","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-08-07T08:07:46.461071Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"80bb4eac-f912-485a-ad2e-56fa71418bd5","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:55:44.684712Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"a2bbf1df-983b-5486-bdfe-04626a0264b6","score_usage_ref":"fmb-live-runs-fsa.json#80bb4eac-f912-485a-ad2e-56fa71418bd5","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-25T18:54:35.726011Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"68f2a44d-b81c-5236-99bc-98bec1ae9765","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:42:14.851402Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-5af28c3816dab44320f023c285c15d3e3ed9fbd5063c384ac1b462ef2b398d0a","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"a411f036-8083-505c-a796-cc9e4f2f2c26","score_usage_ref":"fmb-live-runs-capstone.json#68f2a44d-b81c-5236-99bc-98bec1ae9765","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:48.145945Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"acab39aa-83b9-5fbe-bf1a-ff0255770030","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:33:35.016449Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cc67c176ea6b2dfd3786955295723e7abe2b413c7adaa05bf3fc46adee759a6a","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"a4705c48-ff1f-593e-be33-d11a170a4387","score_usage_ref":"fmb-live-runs-fsa.json#acab39aa-83b9-5fbe-bf1a-ff0255770030","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-08-07T08:05:49.793616Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"57096feb-38d0-5aa1-811a-cd24ebc5612e","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:25:48.433232Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cc67c176ea6b2dfd3786955295723e7abe2b413c7adaa05bf3fc46adee759a6a","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"a4e78b69-c3e1-5f1f-87b4-e089cb17e10f","score_usage_ref":"fmb-live-runs-fin-ma.json#57096feb-38d0-5aa1-811a-cd24ebc5612e","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-08-07T08:05:26.927729Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Opus 5","anthropic/claude-opus-5","claude-opus-5"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"7c670aee-8071-45de-86c5-69b2aad28e1e","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:20:02.981766Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/anthropic","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-opus-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-ef66eed2187cc09eaac374abe4b2b30dea66e50ad713493b2ce3b90806157fd0","display_name":"Claude Opus 5","execution_status":"completed","model_key":"anthropic/claude-opus-5","provider_label":"Anthropic","ranking_state":"current","requested_model_id":"anthropic/claude-opus-5","revision_state":"original","run_id":"a75f0bf5-239f-5da3-a4ac-1da01fbc8aac","score_usage_ref":"fmb-live-runs-fin-capbud.json#7c670aee-8071-45de-86c5-69b2aad28e1e","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-26T09:12:41.818561Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"b13613d8-55c7-46b9-8938-460ea15a9b2f","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-16T14:29:40.518687Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-c85fbc69852728714db01ed690c90b60100854c267f1a3ab041ed4d9963338b6","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"a95ee2a9-fd70-582d-a542-877e8bc55c6a","score_usage_ref":"fmb-live-runs.json#b13613d8-55c7-46b9-8938-460ea15a9b2f","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-16T14:13:43.727065Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"8e1cc1dc-29e9-4d75-b692-32cfefd1fa4a","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T08:55:39.515544Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-ef35aa140459d269d244a80213bd2ef39df837b9119cedcba3ff57f968259dd0","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"aa168065-ecdb-5c2a-984d-8676b374c1dd","score_usage_ref":"fmb-live-runs-fin-ma.json#8e1cc1dc-29e9-4d75-b692-32cfefd1fa4a","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T08:52:01.20469Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash","deepseek-v4-flash","deepseek/deepseek-v4-flash"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"ede46865-e22b-4f86-8d5a-01c6d0f23cbe","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:10:02.474713Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-d232cb4e8278f94a8ac41cf5dc8d11517a7a18bfe988096525d0f1dc93a30907","display_name":"DeepSeek V4 Flash","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash","provider_label":"Alibaba Cloud","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash","revision_state":"original","run_id":"b267168d-0c48-5501-904b-40b1a3d01e1a","score_usage_ref":"fmb-live-runs-hgb.json#ede46865-e22b-4f86-8d5a-01c6d0f23cbe","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-17T10:02:23.05316Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"c837c093-0b64-4b62-8b59-012d7e1b3042","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:06:29.617138Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-782fb79167e127248a0eb252629f33ffc38f450b2a06d8d237848fe302658a26","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"b3137ac7-ec2d-5d68-ab47-ba41003d01e7","score_usage_ref":"fmb-live-runs-fsa.json#c837c093-0b64-4b62-8b59-012d7e1b3042","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T10:02:25.399636Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"581a7a81-24b1-4bed-954d-e739956651d6","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T16:35:13.605411Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-24393c158bcc48e83c42fd72fa6a71637daf639921a9b8a2636fbfff310c6e1d","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"b4351a17-5605-5128-a191-09744f027557","score_usage_ref":"fmb-live-runs-fin-val.json#581a7a81-24b1-4bed-954d-e739956651d6","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-25T16:16:44.992452Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.8 Max","qwen/qwen3.8-max","qwen3.8-max"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"c87e5014-36d0-5b5e-a26a-f5754191b063","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T09:13:52.046502Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.8-max","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-f289f9271dda9e6e744fd27efcbc64d6947cdf8c06cf4bf9c1d1a9c9e93c3fe0","display_name":"Qwen3.8 Max","execution_status":"completed","model_key":"qwen/qwen3.8-max","provider_label":"Alibaba","ranking_state":"current","requested_model_id":"qwen/qwen3.8-max","revision_state":"original","run_id":"b9f4bf26-6dad-53d4-a0a6-42597f9441de","score_usage_ref":"fmb-live-runs-fin-wacc.json#c87e5014-36d0-5b5e-a26a-f5754191b063","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-08-07T08:07:14.121348Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-KNOW-ACC-01","benchmark_version":"0.1.0-dev","campaign_id":"8d9438e2-153d-54fc-8eb4-bbe887d287c4","comparison_group_id":"accounting-knowledge-0.1.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T06:41:41.193733Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"bb2c31e4-b734-5637-8a11-f76f695f9cc9","score_usage_ref":"fmb-live-runs.json#8d9438e2-153d-54fc-8eb4-bbe887d287c4","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"0bae13a5-a0c9-44fb-b6df-6bc83a6847d5","started_at":"2026-07-27T06:33:04.771029Z","suite_id":"accounting-knowledge","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"5bd4b9b9-2e69-44cf-b142-f839ee2b829a","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T12:17:36.805388Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-81589f9684b8a65f84752031b12b547d49a393bc9fc5dfcdb9ed1abdc029261f","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"bc1ba94a-155c-522e-b1bb-b4e69b482042","score_usage_ref":"fmb-live-runs-ifrs.json#5bd4b9b9-2e69-44cf-b142-f839ee2b829a","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-17T12:06:45.80717Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"674918be-289c-4fd0-9a10-517c5e852639","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:23:58.343433Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"bc275c43-bdf4-5725-8145-4f9f70875e09","score_usage_ref":"fmb-live-runs-fin-wacc.json#674918be-289c-4fd0-9a10-517c5e852639","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-26T09:22:51.305631Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"367b3b25-259f-5466-8e2f-1b8faa2b4365","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:39:10.372733Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-58353b1a3da1d308bba6fcd143d0808790725b421eaac69aaf3489a81840a2cf","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"bca84a08-d1f5-5ff9-83db-659a561aba75","score_usage_ref":"fmb-live-runs-capstone.json#367b3b25-259f-5466-8e2f-1b8faa2b4365","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:45.555338Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"6e7b2030-8926-5362-adf1-b7cf7450af08","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:49:08.004296Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-503735f1638b12bba23e0d8d1319a08bcb736e832e9d6af4c9e5ccd552ecea24","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"bd44dd67-a3ce-5b55-9bcd-f74093e80743","score_usage_ref":"fmb-live-runs-capstone.json#6e7b2030-8926-5362-adf1-b7cf7450af08","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:18:02.35983Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Fable 5","anthropic/claude-fable-5","claude-fable-5"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"b55e3a8b-8900-54a2-a2ad-10bdefa7ddf4","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T10:32:42.151463Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/amazon-bedrock/claude-on-aws","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-fable-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-922917b6905f7784c979ad666139c7619bc3f102210186ca640c6a3565cd65c0","display_name":"Claude Fable 5","execution_status":"completed","model_key":"anthropic/claude-fable-5","provider_label":"Amazon Bedrock","ranking_state":"current","requested_model_id":"anthropic/claude-fable-5","revision_state":"original","run_id":"bf372bff-294d-53a2-adf1-a9b16a0a0925","score_usage_ref":"fmb-live-runs-fin-ma.json#b55e3a8b-8900-54a2-a2ad-10bdefa7ddf4","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-08-07T10:29:30.898667Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"6b301eae-9be8-48d3-a43f-0e37c8f1915e","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T11:54:46.325575Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/us-east-2","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-42ef5257ae90b31f1e29fd6d06e548ddbe9bfa4d3ccc60ad4e456187cda14055","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure US East","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"c2663de9-b2be-549f-855b-efefc1bd494d","score_usage_ref":"fmb-live-runs-fin-ma.json#6b301eae-9be8-48d3-a43f-0e37c8f1915e","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-23T11:50:03.351261Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.5 Flash","gemini-3.5-flash","google/gemini-3.5-flash"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"d14147da-a257-4a9e-8990-970121701bfe","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:56:27.841806Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/google-vertex","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.5-flash","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-b96e71013f467814bddadef91d99806c120e4e768913d84cdeefe91453522e75","display_name":"Gemini 3.5 Flash","execution_status":"completed","model_key":"google/gemini-3.5-flash","provider_label":"Google Vertex AI","ranking_state":"current","requested_model_id":"google/gemini-3.5-flash","revision_state":"original","run_id":"c2c7d729-d6bf-5e76-a5d0-0f46cc960fb0","score_usage_ref":"fmb-live-runs-fsa.json#d14147da-a257-4a9e-8990-970121701bfe","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T10:54:01.067218Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Fable 5","anthropic/claude-fable-5","claude-fable-5"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"d24168fc-43a1-56b0-94a8-c6346a883c30","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T10:13:32.737978Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/amazon-bedrock/claude-on-aws","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-fable-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-922917b6905f7784c979ad666139c7619bc3f102210186ca640c6a3565cd65c0","display_name":"Claude Fable 5","execution_status":"completed","model_key":"anthropic/claude-fable-5","provider_label":"Amazon Bedrock","ranking_state":"current","requested_model_id":"anthropic/claude-fable-5","revision_state":"original","run_id":"c51f15f1-7354-53c9-89a1-2e482166e3c4","score_usage_ref":"fmb-live-runs-hgb.json#d24168fc-43a1-56b0-94a8-c6346a883c30","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-08-07T08:08:41.606728Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.6 Flash","gemini-3.6-flash","google/gemini-3.6-flash"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"2dc1c584-a240-58fb-9f4a-e58740a7c6f9","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:30:22.430134Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/google-ai-studio","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.6-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cca7ac27b204ad734de7853d84e62833ab8a4387bf5c22feb38947dd15218f84","display_name":"Gemini 3.6 Flash","execution_status":"completed","model_key":"google/gemini-3.6-flash","provider_label":"Google AI Studio","ranking_state":"current","requested_model_id":"google/gemini-3.6-flash","revision_state":"original","run_id":"c5c0fb31-2b0d-518b-b52d-81077c2ee9a4","score_usage_ref":"fmb-live-runs-fin-val.json#2dc1c584-a240-58fb-9f4a-e58740a7c6f9","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-08-07T08:06:17.577827Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Sol","OpenAI: GPT-5.6 Sol","gpt-5.6-sol","openai/gpt-5.6-sol"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"3bc59934-c013-51f9-b5fa-8b8301af915c","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:14:02.103287Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"262144"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/eu","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-sol","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-1be2d653ab2300292f5b0a350d2b4b1f7b23fe65c0bdac75e8d7ed57a90245d1","display_name":"GPT-5.6 Sol","execution_status":"completed","model_key":"openai/gpt-5.6-sol","provider_label":"Azure EU","ranking_state":"current","requested_model_id":"openai/gpt-5.6-sol","revision_state":"original","run_id":"c639cef1-ddf0-5ec5-b821-0454a96cd061","score_usage_ref":"fmb-live-runs-fin-ma.json#3bc59934-c013-51f9-b5fa-8b8301af915c","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-08-07T08:05:20.210197Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"d919271f-f357-45f2-8f2e-542eebb28003","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T13:26:07.045732Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-ef35aa140459d269d244a80213bd2ef39df837b9119cedcba3ff57f968259dd0","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"c74b9990-dc30-5a76-8389-9b8ffb6e0d4a","score_usage_ref":"fmb-live-runs-fin-val.json#d919271f-f357-45f2-8f2e-542eebb28003","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T13:24:31.606489Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"abddc932-c191-4410-b61d-5f79216d356f","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T12:03:26.153219Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/akashml/fp8","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.6-35b-a3b","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-1c910c57a5709ee2344d09135ccf6f2c2558767b819336f3253b1bbee89d50ae","display_name":"Qwen3.6-35B-A3B","execution_status":"completed","model_key":"qwen/qwen3.6-35b-a3b","provider_label":"AkashML","ranking_state":"current","requested_model_id":"qwen/qwen3.6-35b-a3b","revision_state":"original","run_id":"c7c88804-2dcb-5d84-a2c9-7bfea7231380","score_usage_ref":"fmb-live-runs-fin-val.json#abddc932-c191-4410-b61d-5f79216d356f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T11:56:51.110497Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Fable 5","anthropic/claude-fable-5","claude-fable-5"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"9dc67f6f-515b-52db-b735-2d5503431a67","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:54:44.357279Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/amazon-bedrock/claude-on-aws","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-fable-5","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-922917b6905f7784c979ad666139c7619bc3f102210186ca640c6a3565cd65c0","display_name":"Claude Fable 5","execution_status":"completed","model_key":"anthropic/claude-fable-5","provider_label":"Amazon Bedrock","ranking_state":"current","requested_model_id":"anthropic/claude-fable-5","revision_state":"original","run_id":"cc6cb6ce-4732-5932-b4b8-faf678568b0d","score_usage_ref":"fmb-live-runs-fin-wacc.json#9dc67f6f-515b-52db-b735-2d5503431a67","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-08-07T08:07:11.452161Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"69c38252-e3e5-507e-ad05-4c08906518a5","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:39:45.813223Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-98902f4ce2ff4d7255f148fa8c2c4b7a852cf43e6625d4473af9f2389d821e9a","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Together AI","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"ce3ba458-8f9a-504b-9e34-01e9ad937834","score_usage_ref":"fmb-live-runs-capstone.json#69c38252-e3e5-507e-ad05-4c08906518a5","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:45.555324Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["DeepSeek V4 Flash 0731","deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"25d1cd53-5134-5a48-a32e-8b93f4dd7c47","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T10:10:00.182032Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/fp4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"deepseek/deepseek-v4-flash-0731","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cc67c176ea6b2dfd3786955295723e7abe2b413c7adaa05bf3fc46adee759a6a","display_name":"DeepSeek V4 Flash 0731","execution_status":"completed","model_key":"deepseek/deepseek-v4-flash-0731","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"deepseek/deepseek-v4-flash-0731","revision_state":"original","run_id":"ce4bb2d5-29be-5fcd-a400-2d687ec8bf89","score_usage_ref":"fmb-live-runs-hgb.json#25d1cd53-5134-5a48-a32e-8b93f4dd7c47","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-08-07T08:07:55.479728Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"9c4cdc89-01ff-4a5d-85ad-c268921af71a","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-21T11:38:11.938912Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/wafer","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-567679fd08e34637b20af84d1d06a56d32cc17a06b83b91d641ee127fd914a72","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Wafer","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"d0aa0a2b-d885-5fe9-a22e-5b79409595bf","score_usage_ref":"fmb-live-runs-ifrs.json#9c4cdc89-01ff-4a5d-85ad-c268921af71a","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-21T11:15:53.297862Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Grok 4.5","grok-4.5","x-ai/grok-4.5","xAI: Grok 4.5"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"e61e4479-10cc-45d8-a770-b5638c545dd4","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T10:41:46.899188Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/xai","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"x-ai/grok-4.5","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-ac3540dedb1811b40484ac4ab9a5fa854f2caaa286beb4ab6f3f54a46f3fa288","display_name":"Grok 4.5","execution_status":"completed","model_key":"x-ai/grok-4.5","provider_label":"xAI","ranking_state":"current","requested_model_id":"x-ai/grok-4.5","revision_state":"original","run_id":"d0cbfa56-f9ca-5176-9339-7bff64f5629c","score_usage_ref":"fmb-live-runs-fsa.json#e61e4479-10cc-45d8-a770-b5638c545dd4","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T10:40:18.856936Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"c588b9b3-7270-4820-8aef-e3d53cac2c3f","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:51:43.94046Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"d2405f86-cc2f-5f4c-8951-a94cf7a73167","score_usage_ref":"fmb-live-runs-fin-ma.json#c588b9b3-7270-4820-8aef-e3d53cac2c3f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-25T18:50:31.369803Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"d61daf18-d3c0-474e-9766-2748621a98d5","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T12:23:00.993974Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-db59219469087a896c64c44340211eab8d84a80fc4709262716e98e955921b3c","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"d3fc6847-43aa-5f97-bb5e-e573ed76b80a","score_usage_ref":"fmb-live-runs-hgb.json#d61daf18-d3c0-474e-9766-2748621a98d5","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-17T12:06:46.85575Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K2.6","kimi-k2.6","moonshotai/kimi-k2.6"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"a7d5b932-ec83-49a9-9345-62751fdfcc88","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T15:36:53.189584Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/modelrun/fp4","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k2.6","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-24393c158bcc48e83c42fd72fa6a71637daf639921a9b8a2636fbfff310c6e1d","display_name":"Kimi K2.6","execution_status":"completed","model_key":"moonshotai/kimi-k2.6","provider_label":"ModelRun","ranking_state":"current","requested_model_id":"moonshotai/kimi-k2.6","revision_state":"original","run_id":"d409cf3d-194a-5b38-88f0-0abf9c739edb","score_usage_ref":"fmb-live-runs-fin-wacc.json#a7d5b932-ec83-49a9-9345-62751fdfcc88","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-07-23T14:49:27.828697Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"95d2b3c8-4de7-4119-be5b-2fd0b0dae90f","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T09:51:41.135953Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-782fb79167e127248a0eb252629f33ffc38f450b2a06d8d237848fe302658a26","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"d49b7a4c-a60e-5fda-b70d-2904b3802d38","score_usage_ref":"fmb-live-runs-ifrs.json#95d2b3c8-4de7-4119-be5b-2fd0b0dae90f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-17T09:49:02.083842Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"bf124187-e921-46ba-b385-9401f22bba0d","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:51:52.562447Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"d7161435-8a07-55cb-902c-92bf01ef6c9d","score_usage_ref":"fmb-live-runs-fin-val.json#bf124187-e921-46ba-b385-9401f22bba0d","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-25T18:50:31.370558Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Terra","OpenAI: GPT-5.6 Terra","gpt-5.6-terra","openai/gpt-5.6-terra"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"d5c23926-3530-400d-b27d-2bb93e332bbe","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:53:11.592645Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure","reasoning_effort":"reasoning-max-supported","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-terra","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-54a2e93b7cf6e70137f22d9bc1b8c2c39daeab2620882c5a7031379e0bd72c74","display_name":"GPT-5.6 Terra","execution_status":"completed","model_key":"openai/gpt-5.6-terra","provider_label":"Azure","ranking_state":"current","requested_model_id":"openai/gpt-5.6-terra","revision_state":"original","run_id":"d71ff07f-792a-5cf7-9095-393b29172776","score_usage_ref":"fmb-live-runs-ifrs.json#d5c23926-3530-400d-b27d-2bb93e332bbe","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-25T18:52:05.342414Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Llama 4 Maverick","Meta: Llama 4 Maverick","llama-4-maverick","meta-llama/llama-4-maverick"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"53acb609-9304-4c25-b496-7f7bc45def4c","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T18:55:56.438769Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"16384"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/deepinfra/base","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"meta-llama/llama-4-maverick","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bb2e0f36f468d536259bf55aac3dbccc90ae8d3bae76330120203d122cebc1f6","display_name":"Llama 4 Maverick","execution_status":"completed","model_key":"meta-llama/llama-4-maverick","provider_label":"DeepInfra","ranking_state":"current","requested_model_id":"meta-llama/llama-4-maverick","revision_state":"original","run_id":"d94b124a-15f3-5834-b756-92ae67655bf3","score_usage_ref":"fmb-live-runs-fin-ma.json#53acb609-9304-4c25-b496-7f7bc45def4c","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-07-25T18:54:35.691149Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.6 Flash","gemini-3.6-flash","google/gemini-3.6-flash"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"49d15991-2852-5519-a0e9-555f27c8ade3","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:48:41.736473Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/google-ai-studio","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.6-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cca7ac27b204ad734de7853d84e62833ab8a4387bf5c22feb38947dd15218f84","display_name":"Gemini 3.6 Flash","execution_status":"completed","model_key":"google/gemini-3.6-flash","provider_label":"Google AI Studio","ranking_state":"current","requested_model_id":"google/gemini-3.6-flash","revision_state":"original","run_id":"d9895505-8845-5acc-9482-06cdaecdeb59","score_usage_ref":"fmb-live-runs-fin-capbud.json#49d15991-2852-5519-a0e9-555f27c8ade3","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-08-07T08:07:25.260276Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"7e83a3fe-fefa-4e64-b4f4-4c93b68b41e8","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T09:39:58.202433Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/us-east-2","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-42ef5257ae90b31f1e29fd6d06e548ddbe9bfa4d3ccc60ad4e456187cda14055","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure US East","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"dd660248-a50f-56a9-a1f8-60ef04f19da9","score_usage_ref":"fmb-live-runs-fin-val.json#7e83a3fe-fefa-4e64-b4f4-4c93b68b41e8","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T09:30:24.850475Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Sol","OpenAI: GPT-5.6 Sol","gpt-5.6-sol","openai/gpt-5.6-sol"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"3bed1d6b-0255-5d27-b9c8-7073b774b229","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:39:45.842446Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"262144"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/eu","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-sol","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-1be2d653ab2300292f5b0a350d2b4b1f7b23fe65c0bdac75e8d7ed57a90245d1","display_name":"GPT-5.6 Sol","execution_status":"completed","model_key":"openai/gpt-5.6-sol","provider_label":"Azure EU","ranking_state":"current","requested_model_id":"openai/gpt-5.6-sol","revision_state":"original","run_id":"debdd4df-aa6a-5018-a14b-6006785b0b3e","score_usage_ref":"fmb-live-runs-fin-val.json#3bed1d6b-0255-5d27-b9c8-7073b774b229","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-08-07T08:09:54.376661Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-KNOW-ACC-HGB-02","benchmark_version":"0.2.0-dev","campaign_id":"facb69cb-af2a-471e-88e9-28faf4783259","comparison_group_id":"hgb-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-18T21:47:49.420097Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/moonshotai/int4","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"moonshotai/kimi-k3","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-e655d27b15f277dc1755feacaff749ccea423e9db3ceb7b66c3d556d39c9ca0f","display_name":"Kimi K3","execution_status":"completed","model_key":"moonshotai/kimi-k3","provider_label":"Moonshot AI","ranking_state":"current","requested_model_id":"moonshotai/kimi-k3","revision_state":"original","run_id":"e0c84dae-cf71-54b5-bdb7-3826d0b6d655","score_usage_ref":"fmb-live-runs-hgb.json#facb69cb-af2a-471e-88e9-28faf4783259","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"82d3a8e7-8cba-42c0-a30c-8cf7e38256aa","started_at":"2026-07-18T21:30:53.212104Z","suite_id":"hgb-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Claude Sonnet 5 (Max)","anthropic/claude-sonnet-5","claude-sonnet-5"],"benchmark_id":"FMB-FIN-CAPBUD-01","benchmark_version":"0.2.0-dev","campaign_id":"f68f15de-c830-4e5f-bd0d-25c584bef59e","comparison_group_id":"capital-budgeting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-25T15:49:22.205965Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/us-east-2","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"anthropic/claude-sonnet-5","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-42ef5257ae90b31f1e29fd6d06e548ddbe9bfa4d3ccc60ad4e456187cda14055","display_name":"Claude Sonnet 5 (Max)","execution_status":"completed","model_key":"anthropic/claude-sonnet-5","provider_label":"Azure US East","ranking_state":"current","requested_model_id":"anthropic/claude-sonnet-5","revision_state":"original","run_id":"e1464c20-ff0c-530e-8e7e-12c5affea279","score_usage_ref":"fmb-live-runs-fin-capbud.json#f68f15de-c830-4e5f-bd0d-25c584bef59e","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1ba8e99e-b1c5-4b45-8396-064ab0d81100","started_at":"2026-07-25T15:29:34.278911Z","suite_id":"capital-budgeting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["NVIDIA Nemotron 3 Ultra","nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"d433e863-5ea2-56fb-8542-40393b5aa593","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:46:06.131058Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-bdfae6bbbc4879c2457bce5e1d485a0a13582235620be8cd4739b0da0feb79c5","display_name":"NVIDIA Nemotron 3 Ultra","execution_status":"completed","model_key":"nvidia/nemotron-3-ultra-550b-a55b","provider_label":"Together AI","ranking_state":"current","requested_model_id":"nvidia/nemotron-3-ultra-550b-a55b","revision_state":"original","run_id":"e15cb06d-99ee-57d7-b554-56fdddcd7f48","score_usage_ref":"fmb-live-runs-capstone.json#d433e863-5ea2-56fb-8542-40393b5aa593","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:17:54.118278Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"b3d1073b-daff-4f33-88e9-950d5a42b55f","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-17T12:02:20.629425Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/wafer","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v6","tool_access":"none"},"configuration_key":"config-567679fd08e34637b20af84d1d06a56d32cc17a06b83b91d641ee127fd914a72","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Wafer","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"e3433e86-5d8c-5e35-931c-ab9256189491","score_usage_ref":"fmb-live-runs-fsa.json#b3d1073b-daff-4f33-88e9-950d5a42b55f","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-07-17T11:47:11.41776Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-KNOW-ACC-IFRS-02","benchmark_version":"0.2.0-dev","campaign_id":"059188d4-5f43-4bd0-a030-8a7e5370a1ab","comparison_group_id":"ifrs-reporting-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-26T09:29:28.43012Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"f187861e-b82f-583c-bbfb-d6022169de08","score_usage_ref":"fmb-live-runs-ifrs.json#059188d4-5f43-4bd0-a030-8a7e5370a1ab","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"9dbf3d05-67e5-4bbd-aada-585c12163f1a","started_at":"2026-07-26T09:28:25.774332Z","suite_id":"ifrs-reporting","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GLM 5.2","Z.ai: GLM 5.2","glm-5.2","z-ai/glm-5.2"],"benchmark_id":"FMB-FIN-VAL-01","benchmark_version":"0.2.0-dev","campaign_id":"df4423b0-8bde-4dfd-a3c5-055d72497c93","comparison_group_id":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-23T08:49:39.76957Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/together","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"z-ai/glm-5.2","runtime_mode":"openrouter-tool-free-non-streaming-v7","tool_access":"none"},"configuration_key":"config-4a58c9ad7c51e53df719558cfb405c4d4e384c6467ca475bf906faea4f4a4d6b","display_name":"GLM 5.2","execution_status":"completed","model_key":"z-ai/glm-5.2","provider_label":"Together AI","ranking_state":"current","requested_model_id":"z-ai/glm-5.2","revision_state":"original","run_id":"f420812b-9580-58a7-adb5-afb4e323e3f7","score_usage_ref":"fmb-live-runs-fin-val.json#df4423b0-8bde-4dfd-a3c5-055d72497c93","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","started_at":"2026-07-23T08:47:59.823299Z","suite_id":"valuation-financial-modeling","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Mistral Large 2512","Mistral: Mistral Large 2512","mistral-large-2512","mistralai/mistral-large-2512"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"dbe47734-1b0c-5687-87ca-9e81f03a462a","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-27T04:51:10.487623Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"34000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/mistral","reasoning_effort":"native-default","reasoning_profile":"native-default","requested_model_id":"mistralai/mistral-large-2512","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-2cc9cfac948ba4365b210c7e34d66584e7dc6d8125d305cbb6890f6023636da4","display_name":"Mistral Large 2512","execution_status":"completed","model_key":"mistralai/mistral-large-2512","provider_label":"Mistral AI","ranking_state":"current","requested_model_id":"mistralai/mistral-large-2512","revision_state":"original","run_id":"fca1649b-9e04-5d7d-81c3-2a12a65daa0b","score_usage_ref":"fmb-live-runs-capstone.json#dbe47734-1b0c-5687-87ca-9e81f03a462a","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-26T19:58:24.355992Z","suite_id":"accounting-capstone","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["GPT-5.6 Sol","OpenAI: GPT-5.6 Sol","gpt-5.6-sol","openai/gpt-5.6-sol"],"benchmark_id":"FMB-ANAL-FSA-02","benchmark_version":"0.2.0-dev","campaign_id":"2073ad98-e6c4-5b8e-90fa-82332fa660a9","comparison_group_id":"financial-analysis-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:15:02.842855Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"262144"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"true"}],"provider_route":"openrouter/azure/eu","reasoning_effort":"max","reasoning_profile":"reasoning-max-supported","requested_model_id":"openai/gpt-5.6-sol","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-1be2d653ab2300292f5b0a350d2b4b1f7b23fe65c0bdac75e8d7ed57a90245d1","display_name":"GPT-5.6 Sol","execution_status":"completed","model_key":"openai/gpt-5.6-sol","provider_label":"Azure EU","ranking_state":"current","requested_model_id":"openai/gpt-5.6-sol","revision_state":"original","run_id":"fdb9c733-6e18-532e-b637-6ab56d464e44","score_usage_ref":"fmb-live-runs-fsa.json#2073ad98-e6c4-5b8e-90fa-82332fa660a9","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"6f584818-802d-457a-8d7e-5e6106c40d2a","started_at":"2026-08-07T08:05:39.589777Z","suite_id":"financial-analysis","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Gemini 3.6 Flash","gemini-3.6-flash","google/gemini-3.6-flash"],"benchmark_id":"FMB-FIN-WACC-01","benchmark_version":"0.2.0-dev","campaign_id":"242e4634-529d-5553-9284-f489832938f6","comparison_group_id":"cost-of-capital-financing-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:48:46.177126Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/google-ai-studio","reasoning_effort":"high","reasoning_profile":"reasoning-max-supported","requested_model_id":"google/gemini-3.6-flash","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-cca7ac27b204ad734de7853d84e62833ab8a4387bf5c22feb38947dd15218f84","display_name":"Gemini 3.6 Flash","execution_status":"completed","model_key":"google/gemini-3.6-flash","provider_label":"Google AI Studio","ranking_state":"current","requested_model_id":"google/gemini-3.6-flash","revision_state":"original","run_id":"fe337421-d1ea-5d85-a800-cb109fbc1f35","score_usage_ref":"fmb-live-runs-fin-wacc.json#242e4634-529d-5553-9284-f489832938f6","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"13845652-e210-4c44-9e82-543756b4d83f","started_at":"2026-08-07T08:07:04.061486Z","suite_id":"cost-of-capital-financing","tool_access":"none","validity":"provisional","visibility":"public"},{"aliases":["Qwen3.8 Max","qwen/qwen3.8-max","qwen3.8-max"],"benchmark_id":"FMB-FIN-MA-01","benchmark_version":"0.2.0-dev","campaign_id":"d4a86242-3293-57ae-8b14-2c0b03b82dbe","comparison_group_id":"ma-lbo-capital-allocation-0.2.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-08-07T08:24:07.287613Z","configuration":{"comparison_protocol":"configuration_specific","material_parameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"provider_route":"openrouter/alibaba","reasoning_effort":"xhigh","reasoning_profile":"reasoning-max-supported","requested_model_id":"qwen/qwen3.8-max","runtime_mode":"openrouter-tool-free-non-streaming-v8","tool_access":"none"},"configuration_key":"config-f289f9271dda9e6e744fd27efcbc64d6947cdf8c06cf4bf9c1d1a9c9e93c3fe0","display_name":"Qwen3.8 Max","execution_status":"completed","model_key":"qwen/qwen3.8-max","provider_label":"Alibaba","ranking_state":"current","requested_model_id":"qwen/qwen3.8-max","revision_state":"original","run_id":"ff979aff-7475-5cb4-a8b1-32392fa08e29","score_usage_ref":"fmb-live-runs-fin-ma.json#d4a86242-3293-57ae-8b14-2c0b03b82dbe","scorer_id":"fmb-live-scorer-v1","scoring_method":"deterministic_only","selection_state":"primary","signed_release_id":"8b83e684-0b1b-4eea-936a-a9796cecd85e","started_at":"2026-08-07T08:05:31.452066Z","suite_id":"ma-lbo-capital-allocation","tool_access":"none","validity":"provisional","visibility":"public"}],"schema_version":"kaelum-bench-public-run-index-v3","timing":{"controlled":null,"lifecycle_semantics":"recorded_wall_clock_lifecycle_bounds"}}
