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

Instruction Following on IFEval (IFEval Score)

94.64IFEval Score

GPT-5-2025-08-07

58.884868.167477.4586.7326May 19, 2026May 21, 2026May 23, 2026May 25, 2026May 27, 2026May 29, 2026Jun 1, 2026
Updated 20h ago

Evaluation Results

MethodLinks
2026.05
94.64
2026.05
94.64
2026.05
94.27
2026.05
93.9
2026.05
93.16
93.16
2026.05
92.98
92.79
2026.05
92.79
2026.05
92.42
92.24
2026.05
91.87
91.68
2026.06
91.31
91.13
2026.05
90.2
2026.05
90.2
2026.05
90.2
2026.05
90.2
90.2
90.02
2026.06
90.02
89.65
2026.05
89.65
89.46
2026.05
89.46
2026.05
88.91
2026.05
88.91
2026.05
88.72
2026.05
88.72
2026.05
88.54
2026.05
88.54
2026.05
88.35
2026.05
88.35
88.17
2026.05
87.8
2026.05
87.62
2026.05
87.06
2026.05
85.77
2026.05
85.4
85.21
84.29
84.1
2026.05
83.92
2026.05
83.73
2026.05
82.44
81.89
2026.05
81.52
2026.05
81.15
80.96
80.04
2026.05
79.85
2026.06
79.48
2026.05
78.93
2026.05
78
2026.05
77.82
2026.05
77.08
76.89
2026.06
76.52
2026.05
75.42
2026.05
75.23
2026.05
75.05
2026.05
74.31
2026.05
73.94
2026.06
73.2
2026.05
72.46
2026.06
72.46
2026.05
72.27
2026.05
71.72
2026.05
71.35
2026.06
71.35
2026.05
70.79
2026.05
70.79
2026.05
69.5
2026.05
69.5
2026.06
68.95
2026.05
68.58
2026.05
68.21
2026.05
68.21
2026.05
68.02
2026.05
67.84
2026.06
67.65
2026.05
66.73
2026.05
66.54
2026.05
63.77
2026.05
61
2026.05
60.26