List your company

Math Reasoning Tasks

Benchmarks

TaskDatasetSOTA resultTrendResults
Math Reasoning Tasks (MultiArith, GSM8K, AddSub, AQUA, SingleEq, SVAMP, MAWPS) (test)
99.7MultiArith
23
Math Reasoning Tasks AIME, MATH500, GSM8K, AMC aggregated (test)
64.04Pass@k Score
9