CSR
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CSR (ARC-Easy, ARC-Challenge, BoolQ, PIQA, SIQA, HellaSwag, OpenBookQA, WinoGrande) zero-shot lm-evaluation-harness v0.4.2
68.95Accuracy
32
CSR (Commonsense Reasoning Suite)
67.3CSR Accuracy
14
CSR zero-shot
5.2CF Score
2