Home Model series GPT unsuffixed models GPT-5 GPT-5 · SWE-bench Verified · GPT-5 发布评测固定子集;500 题中排除 23 题,n=477 · Scores and configurations GPT-5 · SWE-bench Verified · GPT-5 发布评测固定子集;500 题中排除 23 题,n=477 · Scores and configurations GPT-5 record for SWE-bench Verified · GPT-5 发布评测固定子集;500 题中排除 23 题,n=477. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions GPT-5 · SWE-bench Verified scores and configurations Metric and score Configuration and evaluation conditions Sources Pass rate 74.9% Reported 74.9% · Unit % Published 2025-08-07
GPT-5 (high) Settings API reasoning model; the developer release benchmark table labels high reasoning effort. Unknowns none recorded Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol SWE-bench Verified; fixed subset n=477 after excluding 23/500 problems Conditions API GPT-5; high reasoning effort. View this score in rankings
Benchmark versions and metrics Aliases GPT-5 SWE-bench Verified 477-task subset
Pass rate · % · Higher is better