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

Zero-shot Evaluation on 9 diverse tasks zero-shot

73.81Average Accuracy (Zero-shot)

FloatingPoint

29.755641.192852.6364.0672May 25, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.05
73.81
2026.05
73.69
2026.05
73.25
2026.05
72.93
2026.05
72.9
2026.05
72.21
2026.05
71.69
2026.05
71.59
2026.05
71.48
2026.05
71.25
2026.05
71.21
2026.05
71.12
2026.05
70.96
2026.05
70.92
2026.05
70.88
2026.05
70.84
2026.05
70.82
2026.05
70.71
2026.05
70.58
2026.05
70.57
2026.05
70.35
2026.05
70.3
2026.05
70.21
2026.05
70.1
2026.05
70.01
2026.05
69.96
2026.05
68.92
2026.05
68.09
2026.05
67.8
2026.05
67.61
2026.05
67.36
2026.05
67.31
2026.05
67.27
2026.05
67.27
2026.05
67.14
2026.05
67.03
2026.05
66.99
2026.05
66.95
2026.05
66.71
2026.05
66.54
2026.05
66.33
2026.05
66.31
2026.05
66.25
2026.05
66.24
2026.05
66.12
2026.05
65.74
2026.05
65.57
2026.05
65.56
2026.05
65.48
2026.05
65.41
2026.05
65.39
2026.05
65.37
2026.05
65.33
2026.05
65.21
2026.05
65.16
2026.05
65.14
2026.05
65.13
2026.05
65.13
2026.05
64.79
2026.05
64.71
2026.05
64.37
2026.05
64.34
2026.05
64.3
2026.05
64.13
2026.05
64.11
2026.05
64.1
2026.05
63.9
2026.05
63.89
2026.05
63.59
2026.05
63.23
2026.05
63.18
2026.05
63.16
2026.05
62.84
2026.05
62.62
2026.05
62.5
2026.05
62.45
2026.05
62.01
2026.05
61.87
2026.05
61.69
2026.05
61.48
2026.05
61.38
2026.05
61.03
2026.05
60.86
2026.05
57.37
2026.05
31.45