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

IMO-ProofBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Proof writingIMO-ProofBench
Avg@3 Grade Score58.7
11
Mathematical ProofIMO-ProofBench Basic, Advanced, Overall
Advanced Score91.9
9
Mathematical ReasoningIMO ProofBench
Pass@1 Score72.9
1
Showing 3 of 3 rows