Verdict
Evenly split 2–2 across 4 shared benchmarks.
Claude Opus 4.5 2 · GPT-5.3 Codex 2 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Evenly split 2–2 across 4 shared benchmarks. Claude Opus 4.5 leads 2 benchmarks and GPT-5.3 Codex leads 2. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 4.5 and GPT-5.3 Codex have 4 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.