Verdict
Gemini 3.7 Flash leads 10–0 across 10 shared benchmarks.
Gemini 3.6 Flash 0 · Gemini 3.7 Flash 10 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Coding: Gemini 3.7 Flash leads 2–0 across 2 shared coding benchmarks (largest gap: DeepSWE, 65.49 vs 48.56 — single evaluator).
Math: Gemini 3.7 Flash leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 36.59 vs 21.95 — single evaluator).
Reasoning: Gemini 3.7 Flash leads 2–0 across 2 shared reasoning benchmarks (largest gap: SimpleQA Verified, 71.2 vs 68.7 — single evaluator).
Unknown: Gemini 3.7 Flash leads 2–0 across 2 shared unknown benchmarks (largest gap: ProofBench, 58 vs 36 — single evaluator).
Gemini 3.7 Flash leads 10–0 across 10 shared benchmarks. Gemini 3.6 Flash leads 0 benchmarks and Gemini 3.7 Flash leads 10. Higher isn't always better — see the integrity caveats on each benchmark.
Gemini 3.6 Flash and Gemini 3.7 Flash have 10 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Gemini 3.7 Flash leads coding 2–0. Gemini 3.7 Flash leads math 2–0.