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

Mathematical Reasoning on Olympiad Bench (Accuracy)

73.5Accuracy

SkyWork-OR1-Math-7B

2.98821.29439.657.906Sep 30, 2025Nov 1, 2025Dec 4, 2025Jan 6, 2026Feb 7, 2026Mar 12, 2026Apr 14, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.03
73.5
2026.03
72.5
2026.03
57.3
2026.04
56.3
2026.03
56
2026.03
55.6
2026.03
53.3
2026.04
52.6
2026.04
50.8
2026.04
50.7
2026.04
50.5
2026.03
49.8
2026.03
47.9
2026.04
47
2026.04
46.2
2026.04
44.9
2026.04
44.7
2026.04
44.6
2026.04
44.4
2026.04
44.1
2026.03
43.6
2026.04
41.8
2026.03
40.77
2026.04
40.6
2026.03
40.28
2026.03
40.06
2026.04
40
2026.04
39.8
2026.04
39.6
2026.03
39.06
2026.03
38.82
2026.03
38.52
2026.04
38.5
2026.04
37.9
2026.04
37.9
2026.04
37.8
2026.04
37
2026.04
36.3
2026.04
35.9
2026.04
35.6
2026.04
35.4
2026.04
34.7
2026.04
34.1
2026.04
33.9
2026.04
33.8
2026.04
32.2
2026.04
32.2
2026.04
31.8
2026.04
30.8
2026.04
29.7
2025.10
29.6
2025.10
29.3
2026.04
29
2026.04
29
2026.04
28.3
2025.10
27.9
2025.10
26.8
2026.04
26.4
2025.10
26.1
2025.10
25.2
2025.09
22.52
2025.09
22.22
2026.04
21.8
2026.04
21.1
2026.04
21
2026.04
21
2026.04
20.6
2026.04
20.2
2026.04
20
2026.04
19.7
2025.10
19.1
2026.04
19
2025.09
18.85
2025.09
18.22
2025.10
18.1
2025.10
18.1
2025.10
17.5
2025.10
17.3
2025.10
17.2
2026.04
16
2026.04
15.7
2025.09
15.56
2025.09
13.63
2026.04
13.5
2026.04
12.9
2025.10
12.1
2026.04
12.1
2026.04
11.6
2026.04
11.4
2026.04
11
2026.04
10.5
2026.04
10
2025.10
7.9
2026.04
7.6
2026.04
6.8
2026.04
6.5
2026.04
6.5
2026.04
6.4
2026.04
5.9
2026.04
5.7
Showing 100 of 123 rows