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

Downstream Average

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question Answering/ReasoningDownstream Average 0-shot
Average Accuracy60.5
12
Aggregated PerformanceDownstream Average All
Accuracy40.3
4
Showing 2 of 2 rows