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

Accuracy on GPQA

59.4Accuracy

Claude 3.5 Sonnet

9.708822.609435.5148.4106May 8, 2025Jun 29, 2025Aug 21, 2025Oct 13, 2025Dec 4, 2025Jan 26, 2026Mar 20, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.03
59.4
2026.03
56.67
2025.05
55.05
2026.03
53.6
2025.05
52.53
2026.03
51.1
2025.05
51.01
2025.05
50.51
2025.10
49.25
2025.10
48.23
2025.12
47.98
2026.03
47.32
2025.10
47.1
2026.03
46.7
2026.03
46.6
2025.10
45.82
2026.03
45.3
2025.05
44.95
2025.10
44.95
2025.10
44.4
2025.05
43.43
2025.10
43.13
2025.10
42.05
2025.12
41.92
2025.05
41.92
2025.10
41.67
2025.10
41.54
2025.10
41.16
2026.03
39.51
2026.03
39.3
2025.10
38.65
2026.03
38.39
2025.05
38.38
2025.05
38.38
2026.03
37.5
2025.10
36.74
2025.10
36.74
2025.10
36.66
2025.05
35.86
2026.03
34.1
2026.03
33.9
2025.05
32.83
2026.03
32.8
2026.03
32.59
2026.03
29.2
2025.05
27.78
2026.03
26.5
2026.03
24.78
2025.05
23.74
2025.05
22.22
2025.05
21.72
2025.05
18.69
2025.05
16.67
2025.05
16.67
2025.05
13.13
2025.05
11.62
2025.05
11.62