Verdict
o3 leads 11–10 across 21 shared benchmarks.
Claude Sonnet 4.5 10 · o3 11 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: Claude Sonnet 4.5 leads 4–2 across 6 shared reasoning benchmarks (largest gap: SimpleQA Verified, 49.4 vs 30.7 — protocols undisclosed).
Unknown: o3 leads 3–1 across 4 shared unknown benchmarks (largest gap: Mystery Game Puzzles, 21.79 vs 8.57 — protocols undisclosed).
Math: o3 leads 2–0 across 2 shared math benchmarks (largest gap: OTIS Mock AIME 2024-2025, 84.43 vs 77.76 — single evaluator).
o3 leads 11–10 across 21 shared benchmarks. Claude Sonnet 4.5 leads 10 benchmarks and o3 leads 11. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Sonnet 4.5 and o3 have 21 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Sonnet 4.5 leads reasoning 4–2. o3 leads unknown 3–1.