Home Model series GPT unsuffixed models GPT-5.2 GPT-5.2 · SWE-Bench Pro · Public · Scores and configurations GPT-5.2 · SWE-Bench Pro · Public · Scores and configurations GPT-5.2 record for SWE-Bench Pro · Public. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions GPT-5.2 · SWE-Bench Pro scores and configurations Metric and score Configuration and evaluation conditions Sources Task success rate 55.6% Reported 55.6% · Unit % Published Unconfirmed
GPT-5.2 Thinking (xhigh) Settings Highest available API reasoning effort xhigh, except professional benchmark tasks. Unknowns none recorded Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol SWE-Bench Pro public set. Conditions Highest available API reasoning effort xhigh; research environment. View this score in rankings
Benchmark versions and metrics Aliases SWE-Bench Pro (Public)
Task success rate · % · Higher is better