Verdict
Claude Sonnet 4.6 leads 8–6 across 14 shared benchmarks.
Claude Sonnet 4.6 8 · GPT-5 6 · 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: SimpleQA Verified, 50.6 vs 29 — single evaluator).
Unknown: Evenly split 1–1 across 2 shared unknown benchmarks (largest gap: ProofBench, 45 vs 18 — single evaluator).
Claude Sonnet 4.6 leads 8–6 across 14 shared benchmarks. Claude Sonnet 4.6 leads 8 benchmarks and GPT-5 leads 6. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Sonnet 4.6 and GPT-5 have 14 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.