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

Zero-shot Reasoning on Zero-shot Average

66Accuracy

BF16 baseline

47.69652.44857.261.952Jan 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
66
2026.01
63.4
2026.01
60.9
2026.01
60.3
2026.01
59.8
2026.01
54.2
2026.01
53.5
2026.01
51.8
2026.01
50.9
2026.01
49.6
2026.01
48.4