Verdict
GPT-5.6 Sol leads 19–2 across 21 shared benchmarks.
GPT-5.6 Sol 19 · Kimi K3 2 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: GPT-5.6 Sol leads 4–2 across 6 shared unknown benchmarks (largest gap: Mystery Game Puzzles, 53.73 vs 18.48 — protocols undisclosed).
Reasoning: GPT-5.6 Sol leads 4–0 across 4 shared reasoning benchmarks (largest gap: SimpleQA Verified, 69.7 vs 50.6 — protocols undisclosed).
Coding: GPT-5.6 Sol leads 3–0 across 3 shared coding benchmarks (largest gap: FrontierSWE, 32.2 vs 25.87 — single evaluator).
Math: GPT-5.6 Sol leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 82.93 vs 39.02 — single evaluator).
GPT-5.6 Sol leads 19–2 across 21 shared benchmarks. GPT-5.6 Sol leads 19 benchmarks and Kimi K3 leads 2. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-5.6 Sol and Kimi K3 have 21 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 reasoning 4–0. GPT-5.6 Sol leads coding 3–0.