{"benchmark":{"benchmark_id":"financial-model-benchmark","deterministic_points":"600","sub_benchmark_id":"FMB-FIN-WACC-01","tasks_total":60,"total_points":"600"},"generated_at":"2026-07-23T16:03:02.625046Z","runs":[{"campaign_id":"28ba1499-6892-4140-9eb9-f54c0387bc85","completed_at":"2026-07-23T11:54:04.565644Z","execution":{"attempted":60,"invalid_json":4,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":56},"model":{"display_name":"gemini-3.5-flash","provider":"google-vertex/global","reasoning_effort":"high","slug":"google/gemini-3.5-flash"},"score":{"deterministic":{"earned_points":"490","maximum_points":"600"},"earned_points":"490","maximum_points":"600","percentage":"81.6667","rank_eligible":true},"started_at":"2026-07-23T11:51:44.612095Z","status":"final_deterministic","updated_at":"2026-07-23T11:54:04.565644Z","usage":{"actual_cost_usd":"0.9373875","completion_tokens":94228,"prompt_tokens":59557,"total_tokens":153785},"verification":{"level":"deterministic"}},{"campaign_id":"2f8ba2cf-8827-4f70-a331-86af7a48c6f1","completed_at":"2026-07-23T09:04:42.409871Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":60},"model":{"display_name":"qwen3.6-35b-a3b","provider":"akashml/fp8","reasoning_effort":"max","slug":"qwen/qwen3.6-35b-a3b"},"score":{"deterministic":{"earned_points":"480","maximum_points":"600"},"earned_points":"480","maximum_points":"600","percentage":"80.0000","rank_eligible":true},"started_at":"2026-07-23T08:51:21.574258Z","status":"final_deterministic","updated_at":"2026-07-23T09:04:42.409871Z","usage":{"actual_cost_usd":"0.23106712","completion_tokens":224745,"prompt_tokens":45158,"total_tokens":269903},"verification":{"level":"deterministic"}},{"campaign_id":"3de63c84-ef2a-4333-9343-2d8d3cee9b54","completed_at":"2026-07-23T12:00:47.124613Z","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":"140","maximum_points":"600"},"earned_points":"140","maximum_points":"600","percentage":"23.3333","rank_eligible":true},"started_at":"2026-07-23T11:57:54.901063Z","status":"final_deterministic","updated_at":"2026-07-23T12:00:47.124613Z","usage":{"actual_cost_usd":"0.051936","completion_tokens":7726,"prompt_tokens":55656,"total_tokens":63382},"verification":{"level":"deterministic"}},{"campaign_id":"5ec303db-453d-4d9d-b4dc-ed7d78f71379","completed_at":"2026-07-23T15:43:33.057607Z","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":"510","maximum_points":"600"},"earned_points":"510","maximum_points":"600","percentage":"85.0000","rank_eligible":true},"started_at":"2026-07-23T14:59:45.523005Z","status":"final_deterministic","updated_at":"2026-07-23T15:43:33.057607Z","usage":{"actual_cost_usd":"0.069050066","completion_tokens":230719,"prompt_tokens":53861,"total_tokens":284580},"verification":{"level":"deterministic"}},{"campaign_id":"7b4b828d-a528-4a40-ab85-e28d33568da9","completed_at":"2026-07-23T09:56:25.07793Z","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":"440","maximum_points":"600"},"earned_points":"440","maximum_points":"600","percentage":"73.3333","rank_eligible":true},"started_at":"2026-07-23T09:53:20.804239Z","status":"final_deterministic","updated_at":"2026-07-23T09:56:25.07793Z","usage":{"actual_cost_usd":"0.3736192","completion_tokens":42395,"prompt_tokens":68111,"total_tokens":110506},"verification":{"level":"deterministic"}},{"campaign_id":"94bdbb20-fc5e-4083-8b72-0035401fa895","completed_at":"2026-07-23T12:08:42.313237Z","execution":{"attempted":60,"invalid_json":0,"missing":0,"provider_failed":0,"schema_failed":1,"tasks_total":60,"valid":59},"model":{"display_name":"glm-5.2","provider":"together","reasoning_effort":"xhigh","slug":"z-ai/glm-5.2"},"score":{"deterministic":{"earned_points":"130","maximum_points":"600"},"earned_points":"130","maximum_points":"600","percentage":"21.6667","rank_eligible":true},"started_at":"2026-07-23T12:06:46.255888Z","status":"final_deterministic","updated_at":"2026-07-23T12:08:42.313237Z","usage":{"actual_cost_usd":"0.09335916","completion_tokens":9135,"prompt_tokens":47043,"total_tokens":56178},"verification":{"level":"deterministic"}},{"campaign_id":"9a84a2d3-9e3f-4906-9d4c-bd0759d5ccd5","completed_at":"2026-07-23T11:50:59.210232Z","execution":{"attempted":60,"invalid_json":4,"missing":0,"provider_failed":0,"schema_failed":2,"tasks_total":60,"valid":54},"model":{"display_name":"nemotron-3-ultra-550b-a55b","provider":"together","reasoning_effort":"high","slug":"nvidia/nemotron-3-ultra-550b-a55b"},"score":{"deterministic":{"earned_points":"180","maximum_points":"600"},"earned_points":"180","maximum_points":"600","percentage":"30.0000","rank_eligible":true},"started_at":"2026-07-23T10:05:40.288911Z","status":"final_deterministic","updated_at":"2026-07-23T11:50:59.210232Z","usage":{"actual_cost_usd":"0.0946044","completion_tokens":18445,"prompt_tokens":47004,"total_tokens":65449},"verification":{"level":"deterministic"}},{"campaign_id":"a7d5b932-ec83-49a9-9345-62751fdfcc88","completed_at":"2026-07-23T15:36:53.189584Z","execution":{"attempted":60,"invalid_json":1,"missing":0,"provider_failed":0,"schema_failed":0,"tasks_total":60,"valid":59},"model":{"display_name":"kimi-k2.6","provider":"modelrun/fp4","reasoning_effort":"max","slug":"moonshotai/kimi-k2.6"},"score":{"deterministic":{"earned_points":"560","maximum_points":"600"},"earned_points":"560","maximum_points":"600","percentage":"93.3333","rank_eligible":true},"started_at":"2026-07-23T14:49:27.828697Z","status":"final_deterministic","updated_at":"2026-07-23T15:36:53.189584Z","usage":{"actual_cost_usd":"1.0415872","completion_tokens":297867,"prompt_tokens":50854,"total_tokens":348721},"verification":{"level":"deterministic"}},{"campaign_id":"c392290d-1fc0-4ea5-82fc-c950f7b2c241","completed_at":"2026-07-23T14:01:57.86348Z","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":"550","maximum_points":"600"},"earned_points":"550","maximum_points":"600","percentage":"91.6667","rank_eligible":true},"started_at":"2026-07-23T13:26:55.367921Z","status":"final_deterministic","updated_at":"2026-07-23T14:01:57.86348Z","usage":{"actual_cost_usd":"0.9527454","completion_tokens":53032,"prompt_tokens":65785,"total_tokens":118817},"verification":{"level":"deterministic"}},{"campaign_id":"fd42f19f-edf8-424f-a0cb-5babc4662cc1","completed_at":"2026-07-23T13:19:03.807487Z","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":"510","maximum_points":"600"},"earned_points":"510","maximum_points":"600","percentage":"85.0000","rank_eligible":true},"started_at":"2026-07-23T13:04:25.896892Z","status":"final_deterministic","updated_at":"2026-07-23T13:19:03.807487Z","usage":{"actual_cost_usd":"2.551102","completion_tokens":234352,"prompt_tokens":103791,"total_tokens":338143},"verification":{"level":"deterministic"}}],"schema_version":"fmb-live-runs-v3"}
