Verdict
Kimi K3 leads 7–0 across 7 shared benchmarks.
Kimi K2.6 0 · Kimi K3 7 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Math: Kimi K3 leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 39.02 vs 25.64 — single evaluator).
Reasoning: Kimi K3 leads 2–0 across 2 shared reasoning benchmarks (largest gap: SimpleQA Verified, 42.7 vs 38.7 — single evaluator).
Kimi K3 leads 7–0 across 7 shared benchmarks. Kimi K2.6 leads 0 benchmarks and Kimi K3 leads 7. Higher isn't always better — see the integrity caveats on each benchmark.
Kimi K2.6 and Kimi K3 have 7 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Kimi K3 leads math 2–0. Kimi K3 leads reasoning 2–0.