Verdict
GPT-5.6 Sol leads 18–1 across 20 shared benchmarks.
GPT-5.5 1 · GPT-5.6 Sol 18 · 1 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: GPT-5.6 Sol leads 3–1 across 4 shared reasoning benchmarks (largest gap: SimpleQA Verified, 71.6 vs 63.1 — single evaluator).
Unknown: GPT-5.6 Sol leads 4–0 across 4 shared unknown benchmarks (largest gap: ProofBench, 83 vs 50 — single evaluator).
Coding: GPT-5.6 Sol leads 3–0 across 3 shared coding benchmarks (largest gap: MirrorCode, 20 vs 10 — single evaluator).
Math: GPT-5.6 Sol leads 1–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 82.93 vs 72.5 — 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.
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.”
No vendor claims on file for GPT-5.6 Sol.
GPT-5.6 Sol leads 18–1 across 20 shared benchmarks. GPT-5.5 leads 1 benchmark and GPT-5.6 Sol leads 18, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-5.5 and GPT-5.6 Sol have 20 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-5.6 Sol leads unknown 4–0. GPT-5.6 Sol leads coding 3–0.