{"task_set_hash":"664f8c7733fef6efa55c8c122d46434498b4d0ebd22aea2102c81dc5f4b2b4cf","model":{"slug":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","api_model_id":"gpt-5.6-sol","family_slug":"gpt","added_at":"2026-07-09","settings_suffix":"","max_input_tokens":922000,"max_output_tokens":128000,"capabilities":["thinking","image","pdf","structured","batch"]},"aggregates":{"avg_score":81.178795,"tasks_attempted":907,"tasks_passed":625,"tasks_attempted_distinct":232,"tasks_passed_attempt_1":161.666667,"tasks_passed_attempt_2_only":46.666667,"pass_at_n":0.897989,"pass_denominator":232,"avg_cost_usd":0.060889,"latency_p50_ms":0,"latency_p95_ms":0,"pass_rate_ci":{"lower":0.8523371823669814,"upper":0.9306742399888144},"pass_hat_at_n":0.8275862068965517,"cost_per_pass_usd":0.067805,"run_count":3,"verified_runs":0},"settings":{"temperature":null,"thinking_budget":null,"tokens_avg_per_run":1177637,"consistency_pct":81.47},"history":[{"run_id":"403bab26-34a5-4af4-bd10-35e988d589b8","ts":"2026-09-10T21:55:19.100Z","score":81.178479,"cost_usd":14.053005,"tier":"claimed","status":"completed","completed_at":"2026-09-10T23:10:09.788Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":206,"duration_ms":3480327},{"run_id":"55ca6e8d-94c5-4bf3-98a5-9b31487386f2","ts":"2026-09-10T21:31:35.535Z","score":82.199074,"cost_usd":14.047293,"tier":"claimed","status":"completed","completed_at":"2026-09-10T23:08:35.562Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":212,"duration_ms":3575126},{"run_id":"527c20ec-42ad-4111-bf0c-a10702e602a0","ts":"2026-09-10T21:05:01.113Z","score":80.178831,"cost_usd":14.27813,"tier":"claimed","status":"completed","completed_at":"2026-09-10T22:41:56.021Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":207,"duration_ms":3763673}],"failure_modes":[{"code":"AL0104","count":122,"pct":0.225508,"example_message":"Syntax error, ')' expected"},{"code":"AL0000","count":105,"pct":0.194085,"example_message":"App generation failed"},{"code":"AL0132","count":55,"pct":0.101664,"example_message":"'System' does not contain a definition for 'CreateSequentialGuid'"},{"code":"AL0107","count":48,"pct":0.088725,"example_message":"Syntax error, identifier expected. Provide a valid name (letters, digits, and underscores only)."},{"code":"AL0111","count":38,"pct":0.07024,"example_message":"Semicolon expected. Add a semicolon (;) to terminate the statement."},{"code":"AL0105","count":36,"pct":0.066543,"example_message":"Syntax error, identifier expected; 'key' is a keyword"},{"code":"AL0126","count":25,"pct":0.046211,"example_message":"No overload for method 'LogMessage' takes 5 arguments. Candidates: built-in method 'LogMessage(Text, Text, Verbosity, DataClassification, TelemetryScope, Text, Text, [Text], [Text])', built-in method 'LogMessage(Text, Text, Verbosity, DataClassification, TelemetryScope, Dictionary of [Text, Text])'"},{"code":"AL0360","count":18,"pct":0.033272,"example_message":"Text literal was not properly terminated. Use the character ' to terminate the literal."},{"code":"AL0297","count":14,"pct":0.025878,"example_message":"The application object identifier '50100' is not valid. It must be within the allowed ranges '[70000..89999]'."},{"code":"AL0198","count":12,"pct":0.022181,"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)"}],"recent_runs":[{"run_id":"403bab26-34a5-4af4-bd10-35e988d589b8","ts":"2026-09-10T21:55:19.100Z","score":81.178479,"cost_usd":14.053005,"tier":"claimed","status":"completed","completed_at":"2026-09-10T23:10:09.788Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":206,"duration_ms":3480327},{"run_id":"55ca6e8d-94c5-4bf3-98a5-9b31487386f2","ts":"2026-09-10T21:31:35.535Z","score":82.199074,"cost_usd":14.047293,"tier":"claimed","status":"completed","completed_at":"2026-09-10T23:08:35.562Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":212,"duration_ms":3575126},{"run_id":"527c20ec-42ad-4111-bf0c-a10702e602a0","ts":"2026-09-10T21:05:01.113Z","score":80.178831,"cost_usd":14.27813,"tier":"claimed","status":"completed","completed_at":"2026-09-10T22:41:56.021Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":207,"duration_ms":3763673}]}