Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Math Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningMath Suite GSM8K, MATH500, AIME25, AIME26, AMC, Olympiad
GSM8K Score92.4
23
Mathematical ReasoningMath Suite math, gsm8k, aime24, minerva, olympiad
MATH Score73.3
6
Mathematical Problem SolvingMath Suite
GSM8K96.36
4
Showing 3 of 3 rows