Home Model series GPT Codex GPT-5.3 Codex GPT-5.3 Codex · SWE-Bench Pro · Public · Scores and configurations GPT-5.3 Codex · SWE-Bench Pro · Public · Scores and configurations GPT-5.3 Codex 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-5.3 Codex · SWE-Bench Pro scores and configurations Metric and score Configuration and evaluation conditions Sources Task success rate 56.8% Reported 56.8% · Unit % Published Unconfirmed
GPT-5.3 Codex (xhigh) Settings Article footnote says all release evaluations use xhigh reasoning. Unknowns none recorded Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol SWE-Bench Pro public set. Conditions xhigh reasoning effort; article states it evaluates real-world software engineering across four languages. View this score in rankings
Benchmark versions and metrics Aliases SWE-Bench Pro (Public)
Task success rate · % · Higher is better