{"kind":"bench_stack_result","version":"bench-2026.07","stack":"playwright-reference","indexable":true,"source":"fixture","canonical_path":"/bench/bench-2026.07/playwright-reference","markdown_path":"/bench/bench-2026.07/playwright-reference.md","rank":2,"latest_verified_at":"2026-06-11T20:45:00.000Z","submission":{"id":"fixture-playwright-reference-bench-2026-07","version":"bench-2026.07","stack":"playwright-reference","stackLabel":"Playwright Reference","status":"verified","submittedAt":"2026-06-11T12:10:00.000Z","verifiedAt":"2026-06-11T20:45:00.000Z","overallScore":72,"categoryScores":[{"category":"subscriptions","title":"Subscriptions","score":76,"evaluable":30,"success":14,"handoff":7,"partial":6,"blocked":3},{"category":"commerce","title":"Commerce","score":70,"evaluable":28,"success":12,"handoff":7,"partial":5,"blocked":4},{"category":"travel","title":"Travel","score":68,"evaluable":22,"success":8,"handoff":6,"partial":4,"blocked":4},{"category":"finance","title":"Finance","score":73,"evaluable":20,"success":9,"handoff":5,"partial":4,"blocked":2},{"category":"dev_saas_api","title":"Developer SaaS/API","score":78,"evaluable":12,"success":8,"handoff":2,"partial":1,"blocked":1}],"taskFamilies":[{"task":"subscriptions.cancel","taskTitle":"Cancel a subscription","category":"subscriptions","categoryTitle":"Subscriptions","score":76,"evaluable":20,"success":11,"handoff":5,"partial":3,"blocked":1},{"task":"commerce.return_order","taskTitle":"Return an order","category":"commerce","categoryTitle":"Commerce","score":70,"evaluable":18,"success":9,"handoff":4,"partial":3,"blocked":2},{"task":"travel.cancel_booking","taskTitle":"Cancel a booking","category":"travel","categoryTitle":"Travel","score":68,"evaluable":16,"success":6,"handoff":5,"partial":3,"blocked":2},{"task":"finance.dispute_charge","taskTitle":"Dispute a charge","category":"finance","categoryTitle":"Finance","score":73,"evaluable":16,"success":8,"handoff":4,"partial":3,"blocked":1},{"task":"dev_saas_api.find_openapi_spec","taskTitle":"Find an OpenAPI spec","category":"dev_saas_api","categoryTitle":"Developer SaaS/API","score":78,"evaluable":12,"success":8,"handoff":2,"partial":1,"blocked":1}],"traceSummary":{"totalTasks":120,"evaluableTasks":106,"reachedOfficialSurface":94,"correctEvidence":82,"classificationMatches":86,"blockedByCaptcha":6,"heldOutTasks":12,"publicTraceCount":102}}}