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

Physical Commonsense Reasoning on PIQA (Accuracy)

85.91Accuracy

Fanar-27B

50.997260.061169.12578.1889Feb 16, 2025Apr 22, 2025Jun 27, 2025Sep 1, 2025Nov 5, 2025Jan 10, 2026Mar 17, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.03
85.91
2026.02
84.22
2026.03
84.11
2026.02
83.51
2026.03
83.24
2026.02
83.08
2026.03
82.75
2026.03
82.37
2026.02
82.15
2026.03
82.05
2026.03
81.94
2026.02
81.88
2025.07
81.23
2025.07
81.12
2026.03
81.07
2026.02
80.52
2025.07
80.3
2025.07
80.25
2026.03
80.14
2025.07
79.76
2025.07
79.43
2026.03
79.16
2025.07
79
2025.07
78.78
2025.07
78.41
2025.07
78.18
2025.07
78.02
2025.07
77.53
2025.07
75.3
2026.03
74.87
2025.07
74.76
2025.02
74.59
2025.07
74.59
2025.07
74.54
2025.02
74.32
2026.03
74.25
2026.03
73.67
2026.03
73.66
2026.03
73.39
2025.02
73.12
2025.02
72.74
2025.02
72.74
2026.03
72.31
2025.02
71.65
2025.02
71.6
2025.07
70.57
2026.03
70.43
2025.02
69.97
2025.02
69.7
2026.03
69.67
2025.02
69.59
2026.03
69.59
2025.07
69.37
2026.03
69.31
2025.02
69.21
2026.03
69.18
2026.03
68.39
2025.07
67.57
2025.07
67.3
2026.03
64.91
2026.03
64.87
2025.07
63.33
2026.03
62.25
2025.07
61.37
2026.03
60.66
2025.07
60.17
2026.03
59.43
2026.03
58.67
2026.03
58.31
2025.07
58.27
2026.03
58.18
2025.07
56.42
2025.07
54.62
2026.03
54.41
2025.07
53.92
2025.07
52.88
2025.07
52.56
2025.07
52.34