FrontierMath Benchmark Leaderboard | Phaseo

FrontierMath

AI benchmark results and model performance

Type: percentageMath

Recorded Results

6

Average Score

36.50%

Score Range

9.20% - 47.60%

Leading Model (lowest score)

9.20% - o3 mini

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
OpenAI	o3 mini	30 Jan 2025	9.20%	-	Yes	Source
OpenAI	GPT 5.1 Chat	13 Nov 2025	26.70%	inferred alias from gpt-5.1-2025-11-13	Yes	Source
OpenAI	GPT 5.2 Chat	11 Dec 2025	40.30%	inferred alias from gpt-5.2-2025-12-11	Yes	Source
OpenAI	GPT 5 Pro	07 Aug 2025	47.60%	inferred family alias from gpt-5.4 (score=0.4083; benches=19)	Yes	Source
OpenAI	GPT 5 Search API	14 Oct 2025	47.60%	inferred family alias from gpt-5.4 (score=0.3050; benches=19)	Yes	Source
OpenAI	GPT 5.4	05 Mar 2026	47.60%	-	Yes	Source