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

Reasoning on GPQA Diamond (Accuracy)

58.08Accuracy

Sequential MAS + MASPO

8.180821.135434.0947.0446Apr 21, 2026Apr 27, 2026May 4, 2026May 10, 2026May 17, 2026May 23, 2026May 30, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
58.08
2026.05
54.04
2026.05
51.01
2026.05
50.63
2026.05
49.52
2026.05
49.49
2026.05
48.04
2026.05
47.98
2026.05
47.73
2026.05
47.73
2026.05
47.52
2026.05
46.72
2026.05
45.96
2026.05
39.4
2026.05
38.4
2026.04
36.36
2026.05
35.9
2026.04
34.85
2026.04
33.84
2026.04
32.83
2026.05
32.32
2026.05
32.3
2026.04
31.82
2026.04
30.81
2026.05
30.8
2026.04
27.3
2026.04
26.3
2026.04
24.8
2026.05
24.24
2026.04
23.2
2026.05
22.8
2026.05
18.2
2026.05
17.2
2026.05
17.2
2026.05
15.7
2026.04
10.1