{"model":{"slug":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","api_model_id":"claude-opus-4-6","family_slug":"claude","added_at":"2025-10-14","settings_suffix":""},"aggregates":{"avg_score":69.540514,"tasks_attempted":506,"tasks_passed":300,"tasks_attempted_distinct":64,"tasks_passed_attempt_1":46,"tasks_passed_attempt_2_only":7,"pass_at_n":0.828125,"avg_cost_usd":0.356844,"latency_p50_ms":150176,"latency_p95_ms":181680,"pass_rate_ci":{"lower":0.7178655850983409,"upper":0.9012235873268377},"pass_hat_at_n":0.765625,"cost_per_pass_usd":0.430907,"run_count":6,"verified_runs":0},"settings":{"temperature":null,"thinking_budget":null,"tokens_avg_per_run":224748,"consistency_pct":90.63},"history":[{"run_id":"48be80fd-566b-492d-b7fd-58a1d7ff2850","ts":"2026-05-04T23:37:17.408Z","score":71.875,"cost_usd":3.493225,"tier":"claimed"},{"run_id":"30d9daf8-9318-447c-8b24-e347cdb4c302","ts":"2026-05-04T20:18:33.860Z","score":69.117647,"cost_usd":3.62341,"tier":"claimed"},{"run_id":"8d16e67a-639d-4b28-bddc-82bfd0074155","ts":"2026-05-04T16:43:38.341Z","score":71.875,"cost_usd":3.58271,"tier":"claimed"},{"run_id":"99c1b6e8-d39d-40ae-a5d7-058922123f09","ts":"2026-04-25T20:38:02.755Z","score":68.825301,"cost_usd":3.86461,"tier":"claimed"},{"run_id":"3ded2473-5f9c-410e-a28e-8298c8d76b26","ts":"2026-04-25T18:49:49.241Z","score":67.205882,"cost_usd":4.0927,"tier":"claimed"},{"run_id":"4098dca9-3906-454b-8b54-a9b7159b936e","ts":"2026-04-25T16:58:31.859Z","score":68.382353,"cost_usd":4.18139,"tier":"claimed"}],"failure_modes":[{"code":"AL0104","count":670,"pct":0.448161,"example_message":"Syntax error, '=' expected"},{"code":"AL0111","count":211,"pct":0.141137,"example_message":"Semicolon expected. Add a semicolon (;) to terminate the statement."},{"code":"AL0000","count":123,"pct":0.082274,"example_message":"App generation failed"},{"code":"AL0185","count":80,"pct":0.053512,"example_message":"Page '0' is missing"},{"code":"AL0224","count":73,"pct":0.048829,"example_message":"Expression expected. Provide a valid expression (variable, constant, calculation, or method call)."},{"code":"AL0107","count":56,"pct":0.037458,"example_message":"Syntax error, identifier expected. Provide a valid name (letters, digits, and underscores only)."},{"code":"AL0198","count":48,"pct":0.032107,"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":"AL0275","count":48,"pct":0.032107,"example_message":"'Product' is an ambiguous reference between 'Product' defined by the extension 'CentralGauge_CG-AL-M001_2 by CentralGauge (1.0.0.0)' and 'Product' defined by the extension 'CG-AL-M001 Prereq by CentralGauge (1.0.0.0)'."},{"code":"AL0118","count":32,"pct":0.021405,"example_message":"The name 'AreAllApprovalsComplete' does not exist in the current context."},{"code":"AL0105","count":29,"pct":0.019398,"example_message":"Syntax error, identifier expected; 'key' is a keyword"}],"recent_runs":[{"run_id":"48be80fd-566b-492d-b7fd-58a1d7ff2850","ts":"2026-05-04T23:37:17.408Z","score":71.875,"cost_usd":3.493225,"tier":"claimed"},{"run_id":"30d9daf8-9318-447c-8b24-e347cdb4c302","ts":"2026-05-04T20:18:33.860Z","score":69.117647,"cost_usd":3.62341,"tier":"claimed"},{"run_id":"8d16e67a-639d-4b28-bddc-82bfd0074155","ts":"2026-05-04T16:43:38.341Z","score":71.875,"cost_usd":3.58271,"tier":"claimed"},{"run_id":"99c1b6e8-d39d-40ae-a5d7-058922123f09","ts":"2026-04-25T20:38:02.755Z","score":68.825301,"cost_usd":3.86461,"tier":"claimed"},{"run_id":"3ded2473-5f9c-410e-a28e-8298c8d76b26","ts":"2026-04-25T18:49:49.241Z","score":67.205882,"cost_usd":4.0927,"tier":"claimed"},{"run_id":"4098dca9-3906-454b-8b54-a9b7159b936e","ts":"2026-04-25T16:58:31.859Z","score":68.382353,"cost_usd":4.18139,"tier":"claimed"}]}