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

HumanE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Code GenerationHumanE
Accuracy85.2
82
Code ReasoningHumanE
Accuracy84.9
35
Code GenerationHumanE
Pass@192.11
11
Showing 3 of 3 rows