{"task_set_hash":"664f8c7733fef6efa55c8c122d46434498b4d0ebd22aea2102c81dc5f4b2b4cf","model":{"slug":"openrouter/minimax/minimax-m3","display_name":"MiniMax M3","api_model_id":"minimax/minimax-m3","family_slug":"minimax","added_at":"2026-05-31","settings_suffix":"","max_input_tokens":1048576,"max_output_tokens":512000,"capabilities":["thinking","structured","batch"]},"aggregates":{"avg_score":60.939987,"tasks_attempted":1047,"tasks_passed":454,"tasks_attempted_distinct":232,"tasks_passed_attempt_1":115,"tasks_passed_attempt_2_only":36.333333,"pass_at_n":0.652299,"pass_denominator":232,"avg_cost_usd":0.01318,"latency_p50_ms":0,"latency_p95_ms":0,"pass_rate_ci":{"lower":0.5889858500077622,"upper":0.7106502899551058},"pass_hat_at_n":0.5172413793103449,"cost_per_pass_usd":0.020206,"run_count":3,"verified_runs":0},"settings":{"temperature":null,"thinking_budget":null,"tokens_avg_per_run":3060500,"consistency_pct":64.66},"history":[{"run_id":"c7cc50ad-0d94-4581-bc65-5f3a84b26651","ts":"2026-09-11T21:55:42.033Z","score":60.50447,"cost_usd":3.024351,"tier":"claimed","status":"completed","completed_at":"2026-09-12T00:24:54.156Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":149,"duration_ms":3439995},{"run_id":"a0348e3b-5093-4757-b00e-7ffb87d71495","ts":"2026-09-11T21:35:20.168Z","score":60.673352,"cost_usd":2.99013,"tier":"claimed","status":"completed","completed_at":"2026-09-12T00:28:15.678Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":152,"duration_ms":3330143},{"run_id":"75675cb6-b54e-47e9-8005-48004237a745","ts":"2026-09-11T21:11:11.931Z","score":61.638889,"cost_usd":3.15896,"tier":"claimed","status":"completed","completed_at":"2026-09-12T00:26:35.297Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":153,"duration_ms":3481925}],"failure_modes":[{"code":"AL0104","count":274,"pct":0.188835,"example_message":"Syntax error, ')' expected"},{"code":"AL0000","count":256,"pct":0.17643,"example_message":"App generation failed"},{"code":"AL0297","count":123,"pct":0.084769,"example_message":"The application object identifier '50100' is not valid. It must be within the allowed ranges '[70000..89999]'."},{"code":"AL0132","count":121,"pct":0.083391,"example_message":"'JsonToken' does not contain a definition for 'AsDecimal'"},{"code":"AL0185","count":101,"pct":0.069607,"example_message":"Codeunit 'IFieldTransformer' is missing"},{"code":"AL0118","count":72,"pct":0.049621,"example_message":"The name 'Preferred Contact Method' does not exist in the current context."},{"code":"AL0133","count":68,"pct":0.046864,"example_message":"Argument 2: cannot convert from 'Text' to 'Boolean'"},{"code":"AL0107","count":64,"pct":0.044108,"example_message":"Syntax error, identifier expected. Provide a valid name (letters, digits, and underscores only)."},{"code":"AL0198","count":49,"pct":0.03377,"example_message":"Expected one of the application object keywords (table, tableextension, page, pageextension, pagecustomization, profile, profileextension, codeunit, report, reportextension, xmlport, query, controladdin, dotnet, enum, enumextension, interface, permissionset, permissionsetextension, entitlement)"},{"code":"AL0111","count":43,"pct":0.029635,"example_message":"Semicolon expected. Add a semicolon (;) to terminate the statement."}],"recent_runs":[{"run_id":"c7cc50ad-0d94-4581-bc65-5f3a84b26651","ts":"2026-09-11T21:55:42.033Z","score":60.50447,"cost_usd":3.024351,"tier":"claimed","status":"completed","completed_at":"2026-09-12T00:24:54.156Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":149,"duration_ms":3439995},{"run_id":"a0348e3b-5093-4757-b00e-7ffb87d71495","ts":"2026-09-11T21:35:20.168Z","score":60.673352,"cost_usd":2.99013,"tier":"claimed","status":"completed","completed_at":"2026-09-12T00:28:15.678Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":152,"duration_ms":3330143},{"run_id":"75675cb6-b54e-47e9-8005-48004237a745","ts":"2026-09-11T21:11:11.931Z","score":61.638889,"cost_usd":3.15896,"tier":"claimed","status":"completed","completed_at":"2026-09-12T00:26:35.297Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":153,"duration_ms":3481925}]}