Verdict
GPT-5.4 Pro leads 3–2 across 5 shared benchmarks.
Gemini 3.7 Flash 2 · GPT-5.4 Pro 3 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: Gemini 3.7 Flash leads 2–0 across 2 shared reasoning benchmarks (largest gap: SimpleQA Verified, 71.2 vs 47.8 — single evaluator).
GPT-5.4 Pro leads 3–2 across 5 shared benchmarks. Gemini 3.7 Flash leads 2 benchmarks and GPT-5.4 Pro leads 3. Higher isn't always better — see the integrity caveats on each benchmark.
Gemini 3.7 Flash and GPT-5.4 Pro have 5 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 reasoning 2–0.