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

Scientific Reasoning on GPQA Diamond (Accuracy)

80.13Accuracy

Upper Bound

11.458829.286947.11564.9431Jun 3, 2025Aug 2, 2025Oct 1, 2025Dec 1, 2025Jan 30, 2026Mar 31, 2026May 31, 2026
Updated 22h ago

Evaluation Results

MethodLinks
2025.08
80.13-
2025.08
79.12-
2025.08
77.27-
76.78-
75.88-
2026.05
69.42-
2026.05
67.74-
2026.05
67.17-
2025.06
60.61-
2025.08
59.43-
2025.06
56.57-
2026.01
55.1-
2025.08
54.21-
2025.08
54.21-
2025.08
52.36-
2026.01
52-
2026.01
51-
2026.05
48.44-
2026.01
48.1-
2025.08
47.31-
2026.05
47.22-
2026.05
47.22-
2025.08
46.98-
2025.08
46.91-
2025.08
46.91-
2026.05
46.59-
2025.08
46.44-
2025.06
45.96-
2026.05
45.33-
2025.08
44.78-
2026.04
44.4-
2026.05
42.91-
2025.08
42.87-
2026.05
42.86-
2026.05
42.42-
2025.08
42.1-
2026.05
41.89-
2026.05
41.78-
2026.05
41.41-
2026.05
41.4-
2026.05
38.78-
2026.05
36.24-
2026.05
34.47-
2026.05
34.22-
2026.04
33.33-
2026.05
32.58-
2025.08
32.32-
2026.05
32.07-
2026.05
31.82-
2026.05
31.19-
2026.05
31.06-
2026.05
30.18-
2026.04
29.8-
2025.08
29.8-
2026.04
29.3-
2026.04
28.8-
2026.05
28.03-
2026.04
27.8-
2026.04
21.21-
2026.04
19.7-
2026.04
14.14-
2026.04
14.1-
2025.12
-48.99
2025.12
-46.46
2025.12
-37.37
2025.12
-44.95
2025.12
-21.72
2025.12
-42.93
2025.12
-46.96
2025.12
-47.47
2025.12
-58.59
2025.12
-56.06
2025.12
-52.53
2025.12
-54.58
2025.12
-22.22
2025.12
-55.56
2025.12
-50
2025.12
-56.57
2025.12
-62.63
2025.12
-59.09
2025.12
-54.54
2025.12
-58.08
2025.12
-30.81
2025.12
-60.1
2025.12
-59.6
2025.12
-60.1
2025.09
-29.3
2025.09
-28.8
2025.09
-31.8
2025.09
-28.8
2025.09
-31.3
2025.09
-27.3
2025.09
-27.3
2025.09
-30.8
2025.09
-27.3
2025.09
-34.8