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

POLYFACT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multiple-choice factual recallPOLYFACT Low
Accuracy56.93
12
Multiple-choice factual recallPOLYFACT High
Accuracy73.15
12
Showing 2 of 2 rows