Verdict
GPT-5.6 Sol leads 9–0 across 9 shared benchmarks.
GPT-5.6 Sol 9 · Qwen 3.8 Max 0 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Math: GPT-5.6 Sol leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 82.93 vs 46.34 — single evaluator).
Reasoning: GPT-5.6 Sol leads 2–0 across 2 shared reasoning benchmarks (largest gap: SimpleQA Verified, 71.6 vs 46.29 — single evaluator).
Unknown: GPT-5.6 Sol leads 2–0 across 2 shared unknown benchmarks (largest gap: ProofBench, 83 vs 58 — single evaluator).
GPT-5.6 Sol leads 9–0 across 9 shared benchmarks. GPT-5.6 Sol leads 9 benchmarks and Qwen 3.8 Max leads 0. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-5.6 Sol and Qwen 3.8 Max have 9 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 math 2–0. GPT-5.6 Sol leads reasoning 2–0.