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

IMO-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningIMO-Bench
Accuracy57.02
57
Mathematical ReasoningIMO-Bench 400
Pass@14.88
9
Mathematical ReasoningIMO-Bench (n=460)
Tokens per Correct43,638
4
Showing 3 of 3 rows