Verdict
GPT-5 leads 18–2 across 20 shared benchmarks.
GPT-5 18 · o3 2 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: GPT-5 leads 5–1 across 6 shared reasoning benchmarks (largest gap: DeepResearch Bench, 55.13 vs 46.6 — single evaluator).
Math: GPT-5 leads 2–0 across 2 shared math benchmarks (largest gap: OTIS Mock AIME 2024-2025, 91.38 vs 83.87 — single evaluator).
GPT-5 leads 18–2 across 20 shared benchmarks. GPT-5 leads 18 benchmarks and o3 leads 2. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-5 and o3 have 20 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-5 leads reasoning 5–1. GPT-5 leads math 2–0.