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

Text-only Adaptive Benchmark

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multiple-choice Question AnsweringText-only Adaptive Benchmark (ALL)
Pass@1 Acc81
5
Multiple-choice Question AnsweringText-only Adaptive Benchmark L5
Pass@1 Accuracy65
5
Multiple-choice Question AnsweringText-only Adaptive Benchmark L4
Pass@1 Accuracy81
5
Multiple-choice Question AnsweringText-only Adaptive Benchmark L3
Pass@1 Accuracy88
5
Multiple-choice Question AnsweringText-only Adaptive Benchmark L1
Pass@1 Accuracy93
5
Showing 5 of 5 rows