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

Reasoning on GPQA (pass@1)

58.78Pass@1

FP16

27.0635.29543.5351.765Jan 30, 2026Feb 15, 2026Mar 4, 2026Mar 20, 2026Apr 6, 2026Apr 22, 2026May 9, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
58.78
2026.05
58.49
2026.05
57.89
2026.05
57.23
2026.05
56.85
2026.05
56.66
2026.05
55.59
2026.05
53.6
2026.05
53.44
2026.05
52.46
2026.05
52.15
2026.05
51.61
2026.05
48.17
2026.01
48.11
2026.01
47.41
2026.01
47.29
2026.01
46.78
2026.01
46.65
2026.05
46.65
2026.05
46.46
2026.05
46.34
2026.01
46.28
2026.01
46.15
2026.05
46.09
2026.01
46.02
2026.05
45.55
2026.01
45.2
2026.01
44.95
2026.01
43.69
2026.01
43.5
2026.01
42.49
2026.01
42.05
2026.05
40.7
2026.05
36.43
2026.05
36.3
2026.05
35.86
2026.05
35.7
2026.05
33.14
2026.01
32.7
2026.01
32.51
2026.01
31.94
2026.01
31.25
2026.01
31.19
2026.01
28.72
2026.01
28.28