Verdict
GPT-5.4 leads 13–0 across 13 shared benchmarks.
GPT-5.4 13 · Grok 4.20 0 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: GPT-5.4 leads 3–0 across 3 shared reasoning benchmarks (largest gap: SimpleQA Verified, 44.83 vs 35.1 — single evaluator).
Context Learning: GPT-5.4 leads 2–0 across 2 shared context learning benchmarks (largest gap: CL-bench Life, 21.7 vs 11.9 — protocols undisclosed).
Math: GPT-5.4 leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 49 vs 17.07 — single evaluator).
GPT-5.4 leads 13–0 across 13 shared benchmarks. GPT-5.4 leads 13 benchmarks and Grok 4.20 leads 0. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-5.4 and Grok 4.20 have 13 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-5.4 leads reasoning 3–0. GPT-5.4 leads context learning 2–0.