Verdict
Claude Opus 4.6 leads 16–7 across 23 shared benchmarks.
Claude Opus 4.6 16 · GPT-5.2 7 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: Claude Opus 4.6 leads 5–1 across 6 shared reasoning benchmarks (largest gap: SimpleBench, 61.12 vs 34.96 — single evaluator).
Unknown: Claude Opus 4.6 leads 3–1 across 4 shared unknown benchmarks (largest gap: ProofBench, 50 vs 15 — single evaluator).
Agentic: Evenly split 1–1 across 2 shared agentic benchmarks (largest gap: APEX-Agents, 34.4 vs 32.4 — protocols undisclosed).
Math: GPT-5.2 leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 31.7 vs 26.83 — single evaluator).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
Coding
“The new Claude Opus 4.6 improves on its predecessor's coding skills”
No vendor claims on file for GPT-5.2.
Claude Opus 4.6 leads 16–7 across 23 shared benchmarks. Claude Opus 4.6 leads 16 benchmarks and GPT-5.2 leads 7. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 4.6 and GPT-5.2 have 23 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Opus 4.6 leads reasoning 5–1. Claude Opus 4.6 leads unknown 3–1.