Suite
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
16-dataset Suite Aggregate
23.21ARobust
9
Suite 0-shot
70.97Accuracy
5
7-task suite
55.5Average Score (7-task Suite)
3
Zero-shot Suite (CSQA, OBQA, PIQA, SIQA, HellaSwag, WinoG, ARC-e, ARC-c, SciQ)
55.84Average Score
3
7-task suite
48.4Average Accuracy (7-task)
2