{"model":{"slug":"openrouter/deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","api_model_id":"deepseek/deepseek-v4-pro","family_slug":"deepseek","added_at":"2026-04-24","settings_suffix":""},"aggregates":{"avg_score":22.612974,"tasks_attempted":686,"tasks_passed":127,"tasks_attempted_distinct":64,"tasks_passed_attempt_1":30,"tasks_passed_attempt_2_only":4,"pass_at_n":0.53125,"avg_cost_usd":0.046619,"latency_p50_ms":83997,"latency_p95_ms":300306,"pass_rate_ci":{"lower":0.41071875000475133,"upper":0.6482421235595515},"pass_hat_at_n":0.09375,"cost_per_pass_usd":0.087753,"run_count":6,"verified_runs":0},"settings":{"temperature":null,"thinking_budget":null,"tokens_avg_per_run":335535,"consistency_pct":46.88},"history":[{"run_id":"88d9b561-ee9c-4875-b867-966da2741749","ts":"2026-05-05T13:59:43.150Z","score":27.927928,"cost_usd":0.353546,"tier":"claimed"},{"run_id":"d29122fc-9975-48cf-8d8e-02d4fdd77888","ts":"2026-05-05T11:14:16.474Z","score":29.013761,"cost_usd":0.337193,"tier":"claimed"},{"run_id":"0a7fca96-9d44-4436-bf17-6edf802ef66b","ts":"2026-05-05T08:29:04.133Z","score":23.903509,"cost_usd":0.388662,"tier":"claimed"},{"run_id":"9bd420c0-4214-4466-a77c-7c611744ed45","ts":"2026-04-26T06:40:17.386Z","score":14.979339,"cost_usd":0.663309,"tier":"claimed"},{"run_id":"d484f310-e4bc-42e1-bc28-0ea7ba183a81","ts":"2026-04-26T05:44:59.015Z","score":18.913043,"cost_usd":0.400222,"tier":"claimed"},{"run_id":"3b640f0a-4329-4394-a363-f981586e5d1a","ts":"2026-04-26T04:38:01.707Z","score":21.875,"cost_usd":0.840662,"tier":"claimed"}],"failure_modes":[{"code":"AL0104","count":923,"pct":0.322389,"example_message":"Syntax error, '}' expected"},{"code":"AL0000","count":368,"pct":0.128537,"example_message":"App generation failed"},{"code":"AL0111","count":221,"pct":0.077192,"example_message":"Semicolon expected. Add a semicolon (;) to terminate the statement."},{"code":"AL0118","count":188,"pct":0.065665,"example_message":"The name '\"Monthly Fee\"' does not exist in the current context."},{"code":"AL0107","count":177,"pct":0.061823,"example_message":"Syntax error, identifier expected. Provide a valid name (letters, digits, and underscores only)."},{"code":"AL0198","count":170,"pct":0.059378,"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":"AL0132","count":157,"pct":0.054838,"example_message":"'Record \"CG Subscription Plan\"' does not contain a definition for 'Created Date'"},{"code":"AL0185","count":86,"pct":0.030038,"example_message":"Codeunit 'IsolatedStorage' is missing"},{"code":"AL0133","count":76,"pct":0.026546,"example_message":"Argument 2: cannot convert from 'Text' to 'Boolean'"},{"code":"AL0124","count":70,"pct":0.02445,"example_message":"The property 'XmlPortName' cannot be used in this context. Verify the property is available for the current object type."}],"recent_runs":[{"run_id":"88d9b561-ee9c-4875-b867-966da2741749","ts":"2026-05-05T13:59:43.150Z","score":27.927928,"cost_usd":0.353546,"tier":"claimed"},{"run_id":"d29122fc-9975-48cf-8d8e-02d4fdd77888","ts":"2026-05-05T11:14:16.474Z","score":29.013761,"cost_usd":0.337193,"tier":"claimed"},{"run_id":"0a7fca96-9d44-4436-bf17-6edf802ef66b","ts":"2026-05-05T08:29:04.133Z","score":23.903509,"cost_usd":0.388662,"tier":"claimed"},{"run_id":"9bd420c0-4214-4466-a77c-7c611744ed45","ts":"2026-04-26T06:40:17.386Z","score":14.979339,"cost_usd":0.663309,"tier":"claimed"},{"run_id":"d484f310-e4bc-42e1-bc28-0ea7ba183a81","ts":"2026-04-26T05:44:59.015Z","score":18.913043,"cost_usd":0.400222,"tier":"claimed"},{"run_id":"3b640f0a-4329-4394-a363-f981586e5d1a","ts":"2026-04-26T04:38:01.707Z","score":21.875,"cost_usd":0.840662,"tier":"claimed"}]}