Common Sense Reasoning Suite
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Common Sense Reasoning Suite (PIQA, ARC-Easy, ARC-Challenge, BoolQ, HellaSwag, Winogrande) zero-shot (test dev)
79.35PIQA
30
Common Sense Reasoning Suite (PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c, OBQA) zero-shot
81.12PIQA
20
Common Sense Reasoning Suite (OpenbookQA, ARC-E, ARC-C, Winogrande, HellaSwag, PIQA, MathQA)
28OpenbookQA Accuracy
18
Common-sense Reasoning Suite (PIQA, HellaSwag, ARC-C, ARC-E, OBQA) (test)
84.1PIQA Accuracy
18
Common-sense Reasoning Suite PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c, SIQA, BoolQ
56.24Average Accuracy
14
Common-sense Reasoning Suite Zero-shot
52.92Average Accuracy (8 Tasks)
10
Common Sense Reasoning Suite ARC, BoolQ, RTE, Winogrande, TruthfulQA
34ARC Challenge Accuracy
8
Common-sense Reasoning Suite
42.91Average Score (8 tasks)
6
Common Sense Reasoning Suite (PIQA, HellaSwag, WSC, BoolQ, RACE-H) zero-shot
71.22PIQA
5