downstream math reasoning tasks (GSM8K, MATH, SVAMP, ASDiv, MAWPS, TAB, MQA, MMLU STEM, SAT)
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
9 downstream math reasoning tasks (GSM8K, MATH, SVAMP, ASDiv, MAWPS, TAB, MQA, MMLU STEM, SAT) (test)
40.4GSM8K Accuracy
12