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

Average (2WikiMultiHop, MMLU, GSM8k)

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-task ReasoningAverage (2WikiMultiHop, MMLU, GSM8k) (in-distribution)
Accuracy75.2
29
Showing 1 of 1 rows