all the models — AI benchmark observatory
← Benchmarks

FrontierMath

A benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians, covering most major branches of modern mathematics from number theory and real analysis to algebraic geometry and category theory.

id frontiermath · max 1 · 17 models reported

#ModelScore
1GPT-5.6 Sol
OpenAI
0.89
FrontierMath Leaderboard · all the models