Verdict
GPT-5.6 Sol leads 8–2 across 10 shared benchmarks.
GPT-5.4 Pro 2 · GPT-5.6 Sol 8 · 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, 71.6 vs 47.8 — single evaluator).
GPT-5.6 Sol leads 8–2 across 10 shared benchmarks. GPT-5.4 Pro leads 2 benchmarks and GPT-5.6 Sol leads 8. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-5.4 Pro and GPT-5.6 Sol have 10 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.