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

IMO-level math problems

Benchmarks

Task NameDataset NameSOTA ResultTrend
Math Problem Solving200 IMO-level math problems IMO-AnswerBench, IMO-ProofBench, ArXivMath (test)
Pass@1 Accuracy50.6
36
Showing 1 of 1 rows