Verdict
Claude Sonnet 4.5 leads 11–8 across 19 shared benchmarks.
Claude Sonnet 4.5 11 · o4-mini 8 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: Claude Sonnet 4.5 leads 4–1 across 5 shared reasoning benchmarks (largest gap: SimpleBench, 45.16 vs 26.44 — single evaluator).
Unknown: Claude Sonnet 4.5 leads 4–0 across 4 shared unknown benchmarks (largest gap: LMCA, 45.6 vs 31.18 — single evaluator).
Math: o4-mini leads 3–0 across 3 shared math benchmarks (largest gap: OTIS Mock AIME 2024-2025, 81.65 vs 77.76 — single evaluator).
Claude Sonnet 4.5 leads 11–8 across 19 shared benchmarks. Claude Sonnet 4.5 leads 11 benchmarks and o4-mini leads 8. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Sonnet 4.5 and o4-mini have 19 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 unknown 4–0. Claude Sonnet 4.5 leads reasoning 4–1.