Verdict
GPT-5 leads 17–2 across 19 shared benchmarks.
Claude Opus 4.1 2 · GPT-5 17 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: GPT-5 leads 5–0 across 5 shared unknown benchmarks (largest gap: DTBench, 84.45 vs 66.67 — single evaluator).
Reasoning: GPT-5 leads 3–1 across 4 shared reasoning benchmarks (largest gap: HLE, 21.55 vs 7.06 — protocols undisclosed).
Math: GPT-5 leads 2–0 across 2 shared math benchmarks (largest gap: OTIS Mock AIME 2024-2025, 91.38 vs 68.86 — single evaluator).
GPT-5 leads 17–2 across 19 shared benchmarks. Claude Opus 4.1 leads 2 benchmarks and GPT-5 leads 17. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 4.1 and GPT-5 have 19 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-5 leads unknown 5–0. GPT-5 leads reasoning 3–1.