{"id":"clm_B277799CADE6","entity":"openai","predicate":"released","value":"SWE-bench Verified","value_json":{"feed":"openai-news","item":"https://openai.com/index/introducing-swe-bench-verified","tags":{"v":2,"ai":true,"by":"claude-haiku-5-5","on":"2026-11-03","themes":["coding","reasoning"],"release_kind":"research"},"check":{"on":"2026-11-04","url":"https://openai.com/index/introducing-swe-bench-verified","read":"feed","pages":1,"quote":"Introducing SWE-bench Verified. We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues","outcome":"checked"},"evidence":"We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.","extracted_by":"claude-haiku-5-5","primary_source":true},"valid_from":"2024-08-13","valid_to":null,"published":"2024-08-13","recorded":"2026-11-03","confidence":0.7,"status":"valid","assertable":true,"superseded_by":null,"supersedes":[],"first_seen_at":"2026-11-03T23:55:33.918867+00:00","updated_at":"2026-11-04T01:09:03.345166+00:00","sources":[{"url":"https://openai.com/index/introducing-swe-bench-verified","tier":"primary","publisher":"OpenAI","published_at":"2024-08-13T00:00:00+00:00"}],"evidence":{"by":"page-read","on":"2026-11-04","quote":"Introducing SWE-bench Verified. We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues","url":"https://openai.com/index/introducing-swe-bench-verified","read":"feed","excerpt":"We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues."},"legend":{"dates":"valid_from: when the claim took effect (a period figure: the day its period closed). published: the earliest day a source on the record published it (a filing's filing date, a post's date; null when no source carries one). recorded: the day AsOf first held it. A figure can take effect weeks before it is published.","why_not":{},"checked_by":{"page-read":"its source page states the value and the date"}}}