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

GSM8K, Code, LogiQA, Alpaca, UChat

Benchmarks

Task NameDataset NameSOTA ResultTrend
Forgetting analysisGSM8K, Code, LogiQA, Alpaca, UChat (test)
GSM8K Forgetting Rate4.8
15
Showing 1 of 1 rows