Benchmark · MathCompetitive

FrontierMath-Tier-4-2025-07-01-Private

FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.

Updated 2026-05-27
Models tested
40
Top score
37.5
GPT-5.4 Pro
Median
6.3
min 2.1
Top-5 spread
σ 4.9
Competitive

Best score over time · one chart, every benchmark

FRONTIERMATH-TIER-4-2025-07-01-PRIVATE36 MODELS · FRONTIER RUNNING MAX0255075100SCORE ↑Jan 25May 25Sep 25Jan 26May 26RELEASE DATE →benchgecko.ai/benchmark/frontiermath-tier-4-2025-07-01-private · frontier
Frontier on FrontierMath-Tier-4-2025-07-01-Private rose from 4.2 to 37.5 in 13 months · +33.3 points · latest leader GPT-5.4 Pro from OpenAI.
Pink dots = frontier records · 7 totalClick to open model page

Same category · related evaluations