Verdict
Evenly split 2–2 across 4 shared benchmarks.
GPT-4 (Mar 2023) 2 · GPT-4o mini 2 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Math: Evenly split 1–1 across 2 shared math benchmarks (largest gap: OTIS Mock AIME 2024-2025, 6.85 vs 0.46 — single evaluator).
Evenly split 2–2 across 4 shared benchmarks. GPT-4 (Mar 2023) leads 2 benchmarks and GPT-4o mini leads 2. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-4 (Mar 2023) and GPT-4o mini have 4 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.