{"task_set_hash":"664f8c7733fef6efa55c8c122d46434498b4d0ebd22aea2102c81dc5f4b2b4cf","model":{"slug":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","api_model_id":"gpt-5.6-luna","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":70.542865,"tasks_attempted":985,"tasks_passed":538,"tasks_attempted_distinct":232,"tasks_passed_attempt_1":135.333333,"tasks_passed_attempt_2_only":44,"pass_at_n":0.772989,"pass_denominator":232,"avg_cost_usd":0.004,"latency_p50_ms":0,"latency_p95_ms":0,"pass_rate_ci":{"lower":0.7148938543270273,"upper":0.8221897927762263},"pass_hat_at_n":0.6767241379310345,"cost_per_pass_usd":0.005175,"run_count":3,"verified_runs":0},"settings":{"temperature":null,"thinking_budget":null,"tokens_avg_per_run":1327797,"consistency_pct":72.41},"history":[{"run_id":"47d9d727-a304-46ed-9e87-0746c36fda38","ts":"2026-09-11T11:15:38.396Z","score":70.357628,"cost_usd":0.921904,"tier":"claimed","status":"completed","completed_at":"2026-09-11T13:27:35.621Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":179,"duration_ms":3750860},{"run_id":"4c8313eb-73a1-41af-b704-c0f04e9cca67","ts":"2026-09-11T04:24:07.564Z","score":70.829099,"cost_usd":0.930939,"tier":"claimed","status":"completed","completed_at":"2026-09-11T05:36:29.175Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":180,"duration_ms":3439969},{"run_id":"f45b64cf-a915-4b44-9a8b-a8a62fb26456","ts":"2026-09-11T00:29:05.188Z","score":70.441919,"cost_usd":0.931082,"tier":"claimed","status":"completed","completed_at":"2026-09-11T01:35:58.842Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":179,"duration_ms":3429887}],"failure_modes":[{"code":"AL0104","count":216,"pct":0.226653,"example_message":"Syntax error, ')' expected"},{"code":"AL0000","count":198,"pct":0.207765,"example_message":"App generation failed"},{"code":"AL0132","count":104,"pct":0.109129,"example_message":"'List of [Interface INotificationChannel]' does not contain a definition for 'Clear'"},{"code":"AL0107","count":67,"pct":0.070304,"example_message":"Syntax error, identifier expected. Provide a valid name (letters, digits, and underscores only)."},{"code":"AL0111","count":53,"pct":0.055614,"example_message":"Semicolon expected. Add a semicolon (;) to terminate the statement."},{"code":"AL0198","count":40,"pct":0.041973,"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":"AL0105","count":36,"pct":0.037775,"example_message":"Syntax error, identifier expected; 'key' is a keyword"},{"code":"AL0360","count":36,"pct":0.037775,"example_message":"Text literal was not properly terminated. Use the character ' to terminate the literal."},{"code":"AL0118","count":31,"pct":0.032529,"example_message":"The name 'Self' does not exist in the current context."},{"code":"AL0244","count":17,"pct":0.017838,"example_message":"The signature of procedure 'TryOpenRecordRef' does not match the signature required by attribute 'TryFunction': return value is expected to be of type 'None' but found type 'Boolean'. The expected signature is: TryOpenRecordRef()."}],"recent_runs":[{"run_id":"47d9d727-a304-46ed-9e87-0746c36fda38","ts":"2026-09-11T11:15:38.396Z","score":70.357628,"cost_usd":0.921904,"tier":"claimed","status":"completed","completed_at":"2026-09-11T13:27:35.621Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":179,"duration_ms":3750860},{"run_id":"4c8313eb-73a1-41af-b704-c0f04e9cca67","ts":"2026-09-11T04:24:07.564Z","score":70.829099,"cost_usd":0.930939,"tier":"claimed","status":"completed","completed_at":"2026-09-11T05:36:29.175Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":180,"duration_ms":3439969},{"run_id":"f45b64cf-a915-4b44-9a8b-a8a62fb26456","ts":"2026-09-11T00:29:05.188Z","score":70.441919,"cost_usd":0.931082,"tier":"claimed","status":"completed","completed_at":"2026-09-11T01:35:58.842Z","excluded_at":null,"excluded_reason":null,"tasks_attempted":232,"tasks_passed":179,"duration_ms":3429887}]}