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

LiveMathBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningLMB (LiveMathBench)
Accuracy35.8
23
Mathematical ReasoningLiveMathBench 202505
Accuracy32.17
11
Mathematical ReasoningLiveMathBench (full)
Pass@177.54
6
Showing 3 of 3 rows