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

OOD Average

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringOOD Average GPQA & MMLU-Pro
Accuracy83.3
9
RoutingOOD Average (HotpotQA, GPQA, SVAMP)
Acc62.6
5
Showing 2 of 2 rows