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

Zero-shot Question Answering and Commonsense Reasoning on (ARC-C, HellaSwag, PIQA, WinoGrande)

55.8ARC-C Accuracy

FP16

52.36853.25954.1555.041Apr 22, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.04
55.857.176.967.664.4
2026.04
54.156.676.469.564.2
2026.04
52.555.274.466.962.2