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

Commonsense Reasoning on Commonsense Reasoning Benchmarks (HellaSwag, WinoGrande, BoolQ)

73.6HellaSwag

QUEST

67.3668.9870.672.22Apr 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
73.663.27570.6
2026.04
70.86672.9269.91
2026.04
70.465.273.9669.85
2026.04
69.663.672.9268.71
2026.04
67.666.873.9669.45