all the models — AI benchmark observatory
← Benchmarks

SAT Math

SAT Math benchmark from AGIEval containing standardized mathematics questions from the College Board SAT examination, designed to evaluate mathematical reasoning capabilities of foundation models using human-centric assessment methods.

id sat-math · max 1 · 1 models reported

#ModelScore
1GPT-4
OpenAI
0.89
SAT Math Leaderboard · all the models