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

GSM-Infinite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningGSM-Infinite Hard
Accuracy50.4
16
Long-Context Mathematical ReasoningGSM-Infinite
Accuracy87.06
11
Showing 2 of 2 rows