{"benchmark":{"benchmark_id":"financial-model-benchmark","deterministic_points":"600","sub_benchmark_id":"FMB-FIN-VAL-01","tasks_total":60,"total_points":"600"},"generated_at":"2026-08-10T07:30:18Z","runs":[{"campaign_id":"581a7a81-24b1-4bed-954d-e739956651d6","completed_at":"2026-07-25T16:35:13.605411Z","execution":{"attempted":60,"invalid_json":4,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":56},"model":{"display_name":"kimi-k2.6","provider":"modelrun/fp4","reasoning_effort":"max","slug":"moonshotai/kimi-k2.6"},"score":{"deterministic":{"earned_points":"530","maximum_points":"600"},"earned_points":"530","maximum_points":"600","percentage":"88.3333","rank_eligible":true},"started_at":"2026-07-25T16:16:44.992452Z","status":"final_deterministic","updated_at":"2026-07-25T16:35:13.605411Z","usage":{"actual_cost_usd":"0.9165794","completion_tokens":262505,"prompt_tokens":42320,"total_tokens":304825},"verification":{"level":"deterministic"}},{"campaign_id":"5995fb89-11dc-479f-8fc5-7276f40de6b0","completed_at":"2026-07-23T12:04:50.701164Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"gemini-3.5-flash","provider":"google-vertex/global","reasoning_effort":"high","slug":"google/gemini-3.5-flash"},"score":{"deterministic":{"earned_points":"590","maximum_points":"600"},"earned_points":"590","maximum_points":"600","percentage":"98.3333","rank_eligible":true},"started_at":"2026-07-23T12:02:33.986832Z","status":"final_deterministic","updated_at":"2026-07-23T12:04:50.701164Z","usage":{"actual_cost_usd":"0.701349","completion_tokens":69822,"prompt_tokens":48634,"total_tokens":118456},"verification":{"level":"deterministic"}},{"campaign_id":"5eb906b6-e5dd-4877-8dfa-8d331dfed758","completed_at":"2026-07-25T18:54:34.884007Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"llama-4-maverick","provider":"deepinfra/base","reasoning_effort":"native-default","slug":"meta-llama/llama-4-maverick"},"score":{"deterministic":{"earned_points":"210","maximum_points":"600"},"earned_points":"210","maximum_points":"600","percentage":"35.0000","rank_eligible":true},"started_at":"2026-07-25T18:53:15.48584Z","status":"final_deterministic","updated_at":"2026-07-25T18:54:34.884007Z","usage":{"actual_cost_usd":"0.012655","completion_tokens":6982,"prompt_tokens":35347,"total_tokens":42329},"verification":{"level":"deterministic"}},{"campaign_id":"7e83a3fe-fefa-4e64-b4f4-4c93b68b41e8","completed_at":"2026-07-23T09:39:58.202433Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"claude-sonnet-5","provider":"azure/us-east-2","reasoning_effort":"max","slug":"anthropic/claude-sonnet-5"},"score":{"deterministic":{"earned_points":"600","maximum_points":"600"},"earned_points":"600","maximum_points":"600","percentage":"100.0000","rank_eligible":true},"started_at":"2026-07-23T09:30:24.850475Z","status":"final_deterministic","updated_at":"2026-07-23T09:39:58.202433Z","usage":{"actual_cost_usd":"1.440526","completion_tokens":126433,"prompt_tokens":88098,"total_tokens":214531},"verification":{"level":"deterministic"}},{"campaign_id":"a139f514-f098-4aa5-9870-98bc7505b1fe","completed_at":"2026-07-26T09:25:02.29645Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"mistral-large-2512","provider":"mistral","reasoning_effort":"native-default","slug":"mistralai/mistral-large-2512"},"score":{"deterministic":{"earned_points":"220","maximum_points":"600"},"earned_points":"220","maximum_points":"600","percentage":"36.6667","rank_eligible":true},"started_at":"2026-07-26T09:23:59.533125Z","status":"final_deterministic","updated_at":"2026-07-26T09:25:02.29645Z","usage":{"actual_cost_usd":"0.029821","completion_tokens":7363,"prompt_tokens":37706,"total_tokens":45069},"verification":{"level":"deterministic"}},{"campaign_id":"a740efee-bcbe-4287-b885-4095cb381dda","completed_at":"2026-07-23T14:28:09.952615Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"kimi-k3","provider":"moonshotai/int4","reasoning_effort":"max","slug":"moonshotai/kimi-k3"},"score":{"deterministic":{"earned_points":"570","maximum_points":"600"},"earned_points":"570","maximum_points":"600","percentage":"95.0000","rank_eligible":true},"started_at":"2026-07-23T14:03:38.819771Z","status":"final_deterministic","updated_at":"2026-07-23T14:28:09.952615Z","usage":{"actual_cost_usd":"0.6095622","completion_tokens":32045,"prompt_tokens":56556,"total_tokens":88601},"verification":{"level":"deterministic"}},{"campaign_id":"abddc932-c191-4410-b61d-5f79216d356f","completed_at":"2026-07-23T12:03:26.153219Z","execution":{"attempted":60,"invalid_json":1,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":59},"model":{"display_name":"qwen3.6-35b-a3b","provider":"akashml/fp8","reasoning_effort":"max","slug":"qwen/qwen3.6-35b-a3b"},"score":{"deterministic":{"earned_points":"520","maximum_points":"600"},"earned_points":"520","maximum_points":"600","percentage":"86.6667","rank_eligible":true},"started_at":"2026-07-23T11:56:51.110497Z","status":"final_deterministic","updated_at":"2026-07-23T12:03:26.153219Z","usage":{"actual_cost_usd":"0.20006756","completion_tokens":194789,"prompt_tokens":37704,"total_tokens":232493},"verification":{"level":"deterministic"}},{"campaign_id":"bf124187-e921-46ba-b385-9401f22bba0d","completed_at":"2026-07-25T18:51:52.562447Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"gpt-5.6-terra","provider":"azure","reasoning_effort":"max","slug":"openai/gpt-5.6-terra"},"score":{"deterministic":{"earned_points":"580","maximum_points":"600"},"earned_points":"580","maximum_points":"600","percentage":"96.6667","rank_eligible":true},"started_at":"2026-07-25T18:50:31.370558Z","status":"final_deterministic","updated_at":"2026-07-25T18:51:52.562447Z","usage":{"actual_cost_usd":"0.27462","completion_tokens":11681,"prompt_tokens":39762,"total_tokens":51443},"verification":{"level":"deterministic"}},{"campaign_id":"c0a3ce92-6eeb-49e0-be25-de9b78eb8fee","completed_at":"2026-07-23T13:06:00.229685Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"minimax-m3","provider":"morph","reasoning_effort":"max","slug":"minimax/minimax-m3"},"score":{"deterministic":{"earned_points":"190","maximum_points":"600"},"earned_points":"190","maximum_points":"600","percentage":"31.6667","rank_eligible":true},"started_at":"2026-07-23T13:03:18.172624Z","status":"final_deterministic","updated_at":"2026-07-23T13:06:00.229685Z","usage":{"actual_cost_usd":"0.0450306","completion_tokens":7012,"prompt_tokens":47003,"total_tokens":54015},"verification":{"level":"deterministic"}},{"campaign_id":"d919271f-f357-45f2-8f2e-542eebb28003","completed_at":"2026-07-23T13:26:07.045732Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"nemotron-3-ultra-550b-a55b","provider":"together","reasoning_effort":"high","slug":"nvidia/nemotron-3-ultra-550b-a55b"},"score":{"deterministic":{"earned_points":"240","maximum_points":"600"},"earned_points":"240","maximum_points":"600","percentage":"40.0000","rank_eligible":true},"started_at":"2026-07-23T13:24:31.606489Z","status":"final_deterministic","updated_at":"2026-07-23T13:26:07.045732Z","usage":{"actual_cost_usd":"0.0600492","completion_tokens":10286,"prompt_tokens":38366,"total_tokens":48652},"verification":{"level":"deterministic"}},{"campaign_id":"df4423b0-8bde-4dfd-a3c5-055d72497c93","completed_at":"2026-07-23T08:49:39.76957Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"glm-5.2","provider":"together","reasoning_effort":"xhigh","slug":"z-ai/glm-5.2"},"score":{"deterministic":{"earned_points":"190","maximum_points":"600"},"earned_points":"190","maximum_points":"600","percentage":"31.6667","rank_eligible":true},"started_at":"2026-07-23T08:47:59.823299Z","status":"final_deterministic","updated_at":"2026-07-23T08:49:39.76957Z","usage":{"actual_cost_usd":"0.06894456","completion_tokens":6230,"prompt_tokens":38734,"total_tokens":44964},"verification":{"level":"deterministic"}},{"campaign_id":"e136359f-ee10-4ea0-a819-38baeccfe248","completed_at":"2026-07-23T12:46:52.702736Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"deepseek-v4-flash","provider":"alibaba","reasoning_effort":"xhigh","slug":"deepseek/deepseek-v4-flash"},"score":{"deterministic":{"earned_points":"570","maximum_points":"600"},"earned_points":"570","maximum_points":"600","percentage":"95.0000","rank_eligible":true},"started_at":"2026-07-23T12:08:53.5815Z","status":"final_deterministic","updated_at":"2026-07-23T12:46:52.702736Z","usage":{"actual_cost_usd":"0.0472031884","completion_tokens":154180,"prompt_tokens":44517,"total_tokens":198697},"verification":{"level":"deterministic"}},{"campaign_id":"f5515803-ef51-487e-9a24-d8ebb44a013f","completed_at":"2026-07-23T12:32:00.488956Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"grok-4.5","provider":"xai","reasoning_effort":"high","slug":"x-ai/grok-4.5"},"score":{"deterministic":{"earned_points":"450","maximum_points":"600"},"earned_points":"450","maximum_points":"600","percentage":"75.0000","rank_eligible":true},"started_at":"2026-07-23T12:30:00.432878Z","status":"final_deterministic","updated_at":"2026-07-23T12:32:00.488956Z","usage":{"actual_cost_usd":"0.2447872","completion_tokens":24931,"prompt_tokens":58263,"total_tokens":83194},"verification":{"level":"deterministic"}},{"campaign_id":"f9239761-a2a2-4279-b802-2326e24aa04f","completed_at":"2026-07-26T09:33:06.425882Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"claude-opus-5","provider":"anthropic","reasoning_effort":"max","slug":"anthropic/claude-opus-5"},"score":{"deterministic":{"earned_points":"580","maximum_points":"600"},"earned_points":"580","maximum_points":"600","percentage":"96.6667","rank_eligible":true},"started_at":"2026-07-26T09:30:30.521947Z","status":"final_deterministic","updated_at":"2026-07-26T09:33:06.425882Z","usage":{"actual_cost_usd":"0.88674","completion_tokens":17850,"prompt_tokens":88098,"total_tokens":105948},"verification":{"level":"deterministic"}},{"campaign_id":"282234b0-56fa-5f05-81c4-9d21905b7769","completed_at":"2026-08-07T08:37:02.293818Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"deepseek-v4-flash-0731","provider":"deepinfra/fp4","reasoning_effort":"max","slug":"deepseek/deepseek-v4-flash-0731"},"score":{"deterministic":{"earned_points":"590","maximum_points":"600"},"earned_points":"590","maximum_points":"600","percentage":"98.3333","rank_eligible":true},"started_at":"2026-08-07T08:06:17.577896Z","status":"final_deterministic","updated_at":"2026-08-07T08:37:02.293818Z","usage":{"actual_cost_usd":"0.01772883","completion_tokens":77831,"prompt_tokens":44397,"total_tokens":122228},"verification":{"level":"deterministic"}},{"campaign_id":"2dc1c584-a240-58fb-9f4a-e58740a7c6f9","completed_at":"2026-08-07T08:30:22.430134Z","execution":{"attempted":60,"invalid_json":2,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":58},"model":{"display_name":"gemini-3.6-flash","provider":"google-ai-studio","reasoning_effort":"high","slug":"google/gemini-3.6-flash"},"score":{"deterministic":{"earned_points":"580","maximum_points":"600"},"earned_points":"580","maximum_points":"600","percentage":"96.6667","rank_eligible":true},"started_at":"2026-08-07T08:06:17.577827Z","status":"final_deterministic","updated_at":"2026-08-07T08:30:22.430134Z","usage":{"actual_cost_usd":"0.5882475","completion_tokens":70759,"prompt_tokens":38370,"total_tokens":109129},"verification":{"level":"deterministic"}},{"campaign_id":"2e6ce950-8924-5201-95b6-80e89f75b063","completed_at":"2026-08-07T08:41:34.150934Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"qwen3.8-max","provider":"alibaba","reasoning_effort":"xhigh","slug":"qwen/qwen3.8-max"},"score":{"deterministic":{"earned_points":"190","maximum_points":"600"},"earned_points":"190","maximum_points":"600","percentage":"31.6667","rank_eligible":true},"started_at":"2026-08-07T08:09:46.536079Z","status":"final_deterministic","updated_at":"2026-08-07T08:41:34.150934Z","usage":{"actual_cost_usd":"0.552888","completion_tokens":78780,"prompt_tokens":40104,"total_tokens":118884},"verification":{"level":"deterministic"}},{"campaign_id":"3bed1d6b-0255-5d27-b9c8-7073b774b229","completed_at":"2026-08-07T08:39:45.842446Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"gpt-5.6-sol","provider":"azure/eu","reasoning_effort":"max","slug":"openai/gpt-5.6-sol"},"score":{"deterministic":{"earned_points":"600","maximum_points":"600"},"earned_points":"600","maximum_points":"600","percentage":"100.0000","rank_eligible":true},"started_at":"2026-08-07T08:09:54.376661Z","status":"final_deterministic","updated_at":"2026-08-07T08:39:45.842446Z","usage":{"actual_cost_usd":"0.811041","completion_tokens":17950,"prompt_tokens":39762,"total_tokens":57712},"verification":{"level":"deterministic"}},{"campaign_id":"93161fb6-3660-5778-b4b8-3e18f218c851","completed_at":"2026-08-07T08:44:29.520954Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"claude-fable-5","provider":"amazon-bedrock/claude-on-aws","reasoning_effort":"max","slug":"anthropic/claude-fable-5"},"score":{"deterministic":{"earned_points":"600","maximum_points":"600"},"earned_points":"600","maximum_points":"600","percentage":"100.0000","rank_eligible":true},"started_at":"2026-08-07T08:09:54.863656Z","status":"final_deterministic","updated_at":"2026-08-07T08:44:29.520954Z","usage":{"actual_cost_usd":"2.64503","completion_tokens":35281,"prompt_tokens":88098,"total_tokens":123379},"verification":{"level":"deterministic"}}],"schema_version":"fmb-live-runs-v3"}
