Verdict
o3 leads 10–6 across 16 shared benchmarks.
Claude Opus 4.1 6 · o3 10 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: Evenly split 2–2 across 4 shared reasoning benchmarks (largest gap: HLE, 16.3 vs 7.06 — protocols undisclosed).
Unknown: o3 leads 3–1 across 4 shared unknown benchmarks (largest gap: Mystery Game Puzzles, 21.79 vs 12.98 — protocols undisclosed).
o3 leads 10–6 across 16 shared benchmarks. Claude Opus 4.1 leads 6 benchmarks and o3 leads 10. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 4.1 and o3 have 16 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
o3 leads unknown 3–1.