Verdict
o3 leads 12–5 across 17 shared benchmarks.
GPT-5 mini 5 · o3 12 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: o3 leads 4–0 across 4 shared reasoning benchmarks (largest gap: SimpleQA Verified, 49.4 vs 21.6 — protocols undisclosed).
Unknown: o3 leads 3–0 across 3 shared unknown benchmarks (largest gap: Mystery Game Puzzles, 21.79 vs 0.86 — protocols undisclosed).
Math: GPT-5 mini leads 2–0 across 2 shared math benchmarks (largest gap: OTIS Mock AIME 2024-2025, 86.65 vs 84.43 — single evaluator).
o3 leads 12–5 across 17 shared benchmarks. GPT-5 mini leads 5 benchmarks and o3 leads 12. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-5 mini and o3 have 17 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
o3 leads reasoning 4–0. o3 leads unknown 3–0.