{"generated_at":"2026-07-23T16:39:45Z","release_id":"000d4759-6fa4-40f9-8cbf-208192bd88b0","runs":[{"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":["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":["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":["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":["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":"5dd43bb4-18ca-4d38-980d-8324b1f3bbb6","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-22T13:07:28.746451Z","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":"0c068719-b30b-52f5-9e93-61905a907359","score_usage_ref":"fmb-live-runs-capstone.json#5dd43bb4-18ca-4d38-980d-8324b1f3bbb6","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-22T12:12:34.236385Z","suite_id":"accounting-capstone","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":"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":"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-ad1fad2bee423475244800460aa81b6993bd5bc85652416b734683a77df4c832","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":["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-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"3e230dc4-8960-4e79-86bf-47c261c436d1","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-22T13:11:40.602467Z","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":"1b89709d-e54c-5dcb-96d2-35a7f1604a8a","score_usage_ref":"fmb-live-runs-capstone.json#3e230dc4-8960-4e79-86bf-47c261c436d1","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-22T12:15:51.654796Z","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-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":"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":"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-ad1fad2bee423475244800460aa81b6993bd5bc85652416b734683a77df4c832","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":["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":"max","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-ea3b098e28e4fef4e38b7132869cfd267631f42e157a1662124fe9b7146e7881","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":["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":"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":"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-ad1fad2bee423475244800460aa81b6993bd5bc85652416b734683a77df4c832","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":["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":["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":["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":["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":["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":["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":["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":"max","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-ea3b098e28e4fef4e38b7132869cfd267631f42e157a1662124fe9b7146e7881","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":["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":["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":["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":"max","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-82f6c65eaa3fa63505c167871125ffbdb2789d6546f2ccfdf5dfbd3181fb90b6","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":["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":["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":["MiniMax M3","MiniMax: MiniMax M3","minimax-m3","minimax/minimax-m3"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"f930c5db-c795-45a8-9a93-a684e24d6d0a","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-22T13:11:24.878073Z","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":"6d0a8ca4-8141-5377-a279-b5b06b3e1b81","score_usage_ref":"fmb-live-runs-capstone.json#f930c5db-c795-45a8-9a93-a684e24d6d0a","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-22T12:18:27.102772Z","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":["Qwen3.6-35B-A3B","qwen/qwen3.6-35b-a3b"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"07cb6e04-c38a-4d2d-8518-1064c25379ab","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-22T13:16:35.018454Z","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":"7317f280-80ca-5d17-a18f-1df67b79afb2","score_usage_ref":"fmb-live-runs-capstone.json#07cb6e04-c38a-4d2d-8518-1064c25379ab","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-22T12:33:00.522088Z","suite_id":"accounting-capstone","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":["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":"max","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-ea3b098e28e4fef4e38b7132869cfd267631f42e157a1662124fe9b7146e7881","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":["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-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":["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":"max","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-82f6c65eaa3fa63505c167871125ffbdb2789d6546f2ccfdf5dfbd3181fb90b6","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":["Qwen3.6-35B-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":["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":"max","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-ea3b098e28e4fef4e38b7132869cfd267631f42e157a1662124fe9b7146e7881","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":["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":["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":["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-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"3339c72b-9703-4d5e-a96c-aacb9edb836e","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-22T13:01:56.113049Z","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":"99f3712e-647e-5356-bbb1-88e30a869950","score_usage_ref":"fmb-live-runs-capstone.json#3339c72b-9703-4d5e-a96c-aacb9edb836e","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-22T11:53:33.202535Z","suite_id":"accounting-capstone","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":["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":"758db65c-a191-4e72-8d8c-2dee912dd486","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-22T13:02:15.333443Z","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-v7","tool_access":"none"},"configuration_key":"config-709a7e0246833005d2a40eaf59b646d84d1ce40766657eb4b42d873f66a222c7","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":"9cfc2527-fb4c-587e-b15b-c4ca982f49d8","score_usage_ref":"fmb-live-runs-capstone.json#758db65c-a191-4e72-8d8c-2dee912dd486","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-22T11:53:34.465104Z","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-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":"max","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-465730f79203994758b03613fcce4049700b294cb827d2b69491c57ecff00df5","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":["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":["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":["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":"81fae28e-bee9-44e5-91b3-da9d461b7c94","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-22T13:07:18.827963Z","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":"c1153911-1f61-5e57-9aa0-4177ec35ec8f","score_usage_ref":"fmb-live-runs-capstone.json#81fae28e-bee9-44e5-91b3-da9d461b7c94","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-22T12:05:20.294363Z","suite_id":"accounting-capstone","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":["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":"max","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-82f6c65eaa3fa63505c167871125ffbdb2789d6546f2ccfdf5dfbd3181fb90b6","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":["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":["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":"max","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-465730f79203994758b03613fcce4049700b294cb827d2b69491c57ecff00df5","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":["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":["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":["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":["Kimi K3","kimi-k3","moonshotai/kimi-k3"],"benchmark_id":"FMB-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"5dc5bc87-fef2-453a-9f7d-e9802d1a35e4","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-21T08:03:19.950301Z","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":"ed7dc4b1-0af2-53a9-9e00-4fe6a3eeef13","score_usage_ref":"fmb-live-runs-capstone.json#5dc5bc87-fef2-453a-9f7d-e9802d1a35e4","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-21T05:07:25.282Z","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-CAP-ACC-03","benchmark_version":"0.3.0-dev","campaign_id":"11b9b370-4156-4a43-89dd-c2d41f4f8457","comparison_group_id":"accounting-capstone-0.3.0-dev-configuration-specific-v1","comparison_protocol":"configuration_specific","completed_at":"2026-07-22T13:16:24.84994Z","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":"ee26ebcc-f39b-57b7-af87-50a010acde3e","score_usage_ref":"fmb-live-runs-capstone.json#11b9b370-4156-4a43-89dd-c2d41f4f8457","scorer_id":"fmb-live-scorer-v1","scoring_method":"hybrid","selection_state":"primary","signed_release_id":"9d07d6d8-80f4-4bca-9adf-1f436336d09d","started_at":"2026-07-22T12:21:26.867701Z","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-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":"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":"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-ad1fad2bee423475244800460aa81b6993bd5bc85652416b734683a77df4c832","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"}],"schema_version":"kaelum-bench-public-run-index-v2"}
