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

Physical Reasoning on PIQA (Accuracy)

82.5Accuracy

AAAC

49.781658.275866.7775.2642Jul 1, 2025Aug 23, 2025Oct 16, 2025Dec 9, 2025Jan 31, 2026Mar 26, 2026May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
82.5
2026.05
82.3
2026.05
82.2
2026.05
82.1
2026.05
81.8
2025.07
81.34
2025.07
81.23
2025.07
81.12
2025.07
81.12
2025.07
81.07
2025.07
81.01
2025.10
80.96
2025.07
80.85
2025.07
80.36
2025.07
80.3
2026.05
80.3
2025.07
80.25
2025.07
80.2
2025.07
80.14
2026.05
80
2026.05
80
2026.05
80
2025.07
79.92
2026.05
79.9
2025.07
79.76
2025.07
79.76
2025.07
79.71
2025.10
79.49
2025.07
79.27
2026.05
79.2
2025.07
78.18
2025.07
78.07
2025.07
77.97
2025.07
77.97
2026.05
77.93
2025.07
77.8
2025.07
77.58
2025.07
77.53
2025.07
77.53
2025.07
77.42
2025.07
77.42
2025.07
77.31
2025.07
77.31
2025.07
77.31
2025.07
77.04
2025.07
76.99
2025.07
76.71
2025.07
76.61
2025.07
76.22
2025.07
76.12
2025.12
75.9
2025.12
75.9
2025.07
75.9
2025.07
75.84
2025.07
75.57
2025.12
75.52
2025.12
75.46
2025.12
75.46
2025.07
75.46
2025.07
75.3
2025.12
75.24
2025.12
75.24
2026.05
75.09
2025.12
75.08
2025.12
75.08
2025.12
74.97
2025.07
74.81
2025.12
74.59
2025.12
74.54
2025.12
74.54
2025.12
74.27
2025.07
73.23
2025.07
72.8
2025.07
72.52
2025.07
71.65
2025.07
71.33
2026.05
71.11
2025.07
70.89
2025.07
70.02
2025.07
69.59
2025.07
68.5
2025.07
67.19
2025.07
66.76
2025.07
66.16
2025.07
65.78
2026.05
62.81
2025.07
61.64
2025.07
57.83
2025.07
51.63
2026.05
51.04