Verdict
Claude Opus 5 leads 12–5 across 18 shared benchmarks.
Claude Opus 5 12 · Gemini 3.8 Flash 5 · 1 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: Claude Opus 5 leads 5–0 across 5 shared unknown benchmarks (largest gap: ProofBench, 99 vs 48 — single evaluator).
Coding: Claude Opus 5 leads 2–1 across 3 shared coding benchmarks (largest gap: FrontierSWE, 52.01 vs 19.63 — single evaluator).
Reasoning: Gemini 3.8 Flash leads 3–0 across 3 shared reasoning benchmarks (largest gap: SimpleQA Verified, 69.7 vs 59.9 — protocols undisclosed).
Math: Claude Opus 5 leads 1–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 73.17 vs 21.95 — protocols undisclosed).
Claude Opus 5 leads 12–5 across 18 shared benchmarks. Claude Opus 5 leads 12 benchmarks and Gemini 3.8 Flash leads 5, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 5 and Gemini 3.8 Flash have 18 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Opus 5 leads unknown 5–0. Gemini 3.8 Flash leads reasoning 3–0.