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

Mathematical Reasoning on MATH (test) (Pass@1)

94.8Pass@1

GPT-o1

40.40854.52968.6582.771Aug 18, 2023Jan 15, 2024Jun 13, 2024Nov 10, 2024Apr 9, 2025Sep 6, 2025Feb 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2023.08
94.8
2023.08
94.8
2023.08
90
2023.08
90
2023.08
86.5
2023.08
86.5
2023.08
77.8
2023.08
76.6
2023.08
76.6
2023.08
74.5
2026.02
74.29
2026.02
74.27
2026.02
73.79
2026.02
73.66
2026.02
73.59
2026.02
73.52
2026.01
73.2
2026.01
73.2
2026.01
72.9
2026.01
72.1
2026.01
72.1
2026.01
71.8
2026.02
71.42
2023.08
71.1
2023.08
71.1
2026.01
71
2023.08
70.9
2026.01
70.8
2026.01
70.5
2026.01
70.3
2026.01
69.8
2023.08
68.6
2023.08
68.6
2026.01
68.2
2026.01
65.1
2023.08
64.6
2023.08
64.5
2023.08
64.5
2026.01
64
2026.01
64
2026.01
63.8
2026.01
63.8
2026.01
63.3
2026.01
62.9
2026.01
62.8
2026.01
62.5
2026.01
62.5
2026.01
62.2
2023.08
62.1
2026.01
61.9
2026.01
61.6
2023.08
58.8
2026.01
58.8
2023.08
58.6
2026.02
58.28
2026.02
58.26
2026.02
58.23
2026.02
57.16
2026.02
57.04
2026.02
56.64
2023.08
55.6
2023.08
55.4
2026.01
54.5
2026.01
54.1
2023.08
52.6
2023.08
52.6
2026.01
52.5
2026.01
52
2026.01
52
2025.03
51.7
2026.01
51.6
2026.01
51.5
2026.01
51.3
2026.02
51.06
2026.01
51
2026.01
50.9
2026.01
50.7
2025.03
50.6
2023.08
50.6
2026.01
50.6
2026.01
50.5
2023.08
49.9
2023.08
49.9
2026.01
49.8
2026.01
49.5
2023.08
49.2
2023.08
49.2
2026.01
48.6
2023.08
48
2023.08
48
2023.08
47.9
2023.08
47.9
2025.03
45.5
2023.08
45.2
2023.08
43.5
2023.08
43.1
2023.08
43.1
2025.03
42.5
2023.08
42.5
2023.08
42.5
Showing 100 of 151 rows