Verdict
Claude Opus 5 leads 15–7 across 23 shared benchmarks.
Claude Opus 5 15 · GPT-5.6 Sol 7 · 1 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: Claude Opus 5 leads 6–0 across 6 shared unknown benchmarks (largest gap: ProofBench, 99 vs 83 — single evaluator).
Reasoning: Claude Opus 5 leads 2–1 across 4 shared reasoning benchmarks (largest gap: SimpleBench, 76.72 vs 66.04 — single evaluator).
Coding: Claude Opus 5 leads 3–0 across 3 shared coding benchmarks (largest gap: FrontierSWE, 52.01 vs 32.2 — single evaluator).
Agentic: Claude Opus 5 leads 2–0 across 2 shared agentic benchmarks (largest gap: APEX-Agents, 65.8 vs 51.4 — protocols undisclosed).
Game Playing: Evenly split 1–1 across 2 shared game playing benchmarks (largest gap: Chess Puzzles, 66.33 vs 40.03 — protocols undisclosed).
Math: GPT-5.6 Sol leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 82.93 vs 73.17 — single evaluator).
Claude Opus 5 leads 15–7 across 23 shared benchmarks. Claude Opus 5 leads 15 benchmarks and GPT-5.6 Sol leads 7, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 5 and GPT-5.6 Sol have 23 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Opus 5 leads unknown 6–0. Claude Opus 5 leads coding 3–0.