Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

WebGPT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringWebGPT
Average Score76.42
18
Reward ModelingWebGPT
Accuracy58.4
8
Preference ClassificationWebGPT comparisons (test)
Accuracy60.8
7
Showing 3 of 3 rows