Verdict
GPT-5.5 leads 20–3 across 24 shared benchmarks.
Claude Opus 4.6 3 · GPT-5.5 20 · 1 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: GPT-5.5 leads 4–1 across 6 shared unknown benchmarks (largest gap: Mystery Game Puzzles, 51.53 vs 17.38 — protocols undisclosed).
Reasoning: GPT-5.5 leads 4–1 across 5 shared reasoning benchmarks (largest gap: SimpleQA Verified, 63 vs 47 — protocols undisclosed).
Agentic: GPT-5.5 leads 2–0 across 2 shared agentic benchmarks (largest gap: APEX-Agents, 55.1 vs 46.3 — protocols undisclosed).
Coding: GPT-5.5 leads 2–0 across 2 shared coding benchmarks (largest gap: FrontierCode, 42.96 vs 26.64 — single evaluator).
Math: GPT-5.5 leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 72.5 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”
Agentic / Tool Use
“The gains are especially strong in agentic coding, computer use, knowledge work, and early scientific research”
Coding
“It excels at writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, operating software, and moving across tools until a task is finished.”
General
“We're releasing GPT-5.5, our smartest and most intuitive to use model yet, and the next step toward a new way of getting work done on a computer.”
Speed / Latency
“GPT-5.5 matches GPT-5.4 per-token latency in real-world serving, while performing at a much higher level of intelligence.”
GPT-5.5 leads 20–3 across 24 shared benchmarks. Claude Opus 4.6 leads 3 benchmarks and GPT-5.5 leads 20, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 4.6 and GPT-5.5 have 24 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-5.5 leads unknown 4–1. GPT-5.5 leads reasoning 4–1.