Verdict
GPT-5 leads 22–1 across 23 shared benchmarks.
Gemini 2.5 Pro (Jun 2025) 1 · GPT-5 22 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: GPT-5 leads 4–1 across 5 shared reasoning benchmarks (largest gap: ARC-AGI, 65.67 vs 41 — single evaluator).
Unknown: GPT-5 leads 3–0 across 3 shared unknown benchmarks (largest gap: METR Time Horizons, 69.61 vs 55.44 — single evaluator).
Coding: GPT-5 leads 2–0 across 2 shared coding benchmarks (largest gap: Terminal Bench, 49.61 vs 32.64 — single evaluator).
Math: GPT-5 leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 21.95 vs 0 — single evaluator).
GPT-5 leads 22–1 across 23 shared benchmarks. Gemini 2.5 Pro (Jun 2025) leads 1 benchmark and GPT-5 leads 22. Higher isn't always better — see the integrity caveats on each benchmark.
Gemini 2.5 Pro (Jun 2025) and GPT-5 have 23 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-5 leads reasoning 4–1. GPT-5 leads unknown 3–0.