Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Mathematical Reasoning on OlympiadBench Math

99.86Accuracy

HEART

-1.706424.661851.0377.3982Jun 18, 2024Sep 19, 2024Dec 21, 2024Mar 25, 2025Jun 26, 2025Sep 27, 2025Dec 30, 2025
Updated 2d ago

Evaluation Results

MethodLinks
2025.09
99.86
2025.09
94.63
2025.09
94.44
2025.09
93.63
2025.09
92.59
2025.09
83.63
2025.09
77.67
2025.12
77.5
2025.12
77
2025.09
76.93
2025.12
76.3
2025.09
75.44
2025.12
74.9
2025.09
74.41
2025.12
74.2
2025.09
72.78
2025.12
71.5
2025.12
70.9
2025.12
69.7
2025.12
68.8
2025.12
68.1
2025.12
67.4
2025.12
66.3
2025.12
61
2025.12
60.2
2025.12
60.2
2025.09
58.63
2025.12
57.6
2025.09
52.33
2025.12
50.3
2025.12
47.2
2025.12
44.5
2025.09
40.7
2025.12
35.9
2025.12
34.9
2025.12
31.3
2025.12
30.7
2025.03
25.5
2025.03
23.3
2025.03
21.7
2024.06
21.7
2025.03
21.6
2024.06
21.3
2025.03
21
2025.03
19.3
2025.03
19.1
2025.03
19
2024.06
18.7
2025.03
17.2
2025.03
14.7
2025.03
14.5
2025.03
14.2
2025.03
13.6
2025.03
13
2025.03
12.9
2025.03
12.6
2025.03
11.9
2025.03
11.9
2025.03
11
2025.03
10.5
2025.03
10.4
2025.03
10.1
2025.03
9.6
2025.03
9.5
2025.03
9.4
2025.03
9.3
2025.03
9.3
2025.03
8.7
2025.03
8.7
2025.03
7.7
2025.03
7.3
2025.03
5.9
2025.03
5.6
2025.03
5.5
2025.03
5.5
2025.03
5.3
2025.03
5.2
2025.03
5
2025.03
5
2025.03
4.7
2025.03
4.7
2025.03
3.9
2025.03
3.1
2025.03
2.2