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

Math Reasoning on GSM8K

100Accuracy (GSM8K)

GPT-5 high

54.34466.19778.0589.903Oct 28, 2025Dec 9, 2025Jan 20, 2026Mar 3, 2026Apr 14, 2026May 26, 2026Jul 7, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2025.11
100-
2025.11
100-
2025.11
98.9-
2025.11
98.9-
2026.04
96.8-
2026.04
96.5-
2026.04
96.5-
2026.06
96.3-
2026.04
95.6-
2026.04
95-
2026.06
94.8-
2026.04
94.5-
2026.06
94.5-
2026.06
94.1-
2026.04
93.7-
2026.06
93.5-
2026.06
93.1-
2026.06
93-
2026.06
92.9-
2026.06
92.8-
2026.06
92.5-
2026.06
92.4-
2026.06
92.4-
2026.06
89.7-
2026.06
89.2-
2026.06
89.1-
2026.05
88.93-
2026.05
88.79-
2026.05
88.63-
2026.07
88.48-
2026.07
88.25-
2026.07
88.17-
2026.06
87.9-
2026.07
87.26-
2026.05
86.96-
2026.07
86.73-
2026.05
86.54-
2026.05
85.67-
2026.06
85.4-
2026.06
85.1-
2026.06
85-
2026.05
84.91-
2026.05
84.76-
2026.06
84.7-
2026.06
84.2-
2026.05
83.92-
2026.05
83.39-
2026.06
83.3-
2026.06
83.1-
2026.06
83-
2026.05
82.34-
2026.05
81.5-
2026.05
80.44-
2026.07
80.21-
2026.04
78.09-
2026.04
77.31-
2026.06
77.3-
2026.07
77.18-
2026.05
76.88-
2026.04
76.32-
2026.04
75.92-
2026.04
75.89-
2025.11
75.7-
2026.04
74.37-
2026.06
74-
2026.05
72.33-
2026.04
71-
2026.07
70.96-
2026.06
70.3-
2026.04
68.2-
2026.04
68.1-
2025.10
66.4-
2026.04
66.3-
2026.04
66.2-
2025.10
65.8-
2025.10
65.5-
2025.10
64.6-
2025.10
64.3-
2026.04
62.5-
2026.06
61.5-
2026.03
61.256.3
2026.04
60.8-
2026.04
60.7-
2026.03
59.855.5
2026.03
59.755.3
2026.03
5953.4
2026.04
58.9-
2026.06
58.5-
2026.06
58.2-
2026.03
57.953
2026.03
57.852.3
2026.03
57.749.3
2026.04
57.22-
2026.03
57.252.6
2026.03
5750.2
2026.04
56.8-
2026.06
56.6-
2026.04
56.52-
2026.05
56.18-
2026.03
56.150.1
Showing 100 of 190 rows