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

Science Reasoning on GPQA

95.1Accuracy

M2CL

48.40460.52772.6584.773Jan 31, 2025Apr 14, 2025Jun 26, 2025Sep 7, 2025Nov 19, 2025Jan 31, 2026Apr 14, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.02
95.1
2026.02
94.7
2026.02
91.3
2026.02
88.5
2026.04
86.6
2026.02
84.5
2026.04
82.7
2026.02
82
2026.04
80.1
2026.04
80.09
2026.02
80
2025.01
79.7
2026.04
79.23
2026.02
79
2025.01
76.8
2026.02
74.9
2026.02
74.6
2026.02
73.9
2026.02
73.4
2026.02
73.2
2026.02
73
2026.02
72.8
2025.01
71.5
2025.01
70.6
2026.02
70.5
2026.02
69.9
2026.02
69.7
2026.02
69
2026.02
69
2026.02
68.3
2026.02
68
2026.02
67.2
2026.02
67
2025.01
66.7
2026.02
66
2026.02
66
2025.01
65.2
2025.01
63.6
2026.02
63.4
2026.02
63
2025.01
62.6
2025.01
62.1
2025.12
61.56
2025.12
61.51
2025.12
61.21
2025.01
60.6
2026.01
60.6
2026.02
59.7
2025.01
59.6
2025.01
59.6
2026.02
59.6
2026.02
59.6
2026.01
59.6
2025.01
59.1
2025.09
59.1
2026.02
59
2026.02
59
2025.01
58.6
2026.01
58.6
2026.01
58.6
2026.02
58.5
2026.02
58
2025.10
57.75
2025.01
56.6
2026.01
56.6
2026.01
56.6
2026.01
56.1
2026.02
56
2026.02
56
2025.10
55.67
2025.10
55.33
2026.02
55.2
2026.01
55.1
2026.02
54.8
2025.10
54.75
2026.02
54.7
2025.01
54.5
2026.01
54.5
2026.01
54.5
2025.10
54.5
2026.01
54
2025.10
53.75
2026.02
53.6
2026.01
53.5
2025.10
53.33
2026.02
53.3
2025.10
53.25
2026.02
53
2026.01
53
2026.01
53
2025.10
52.59
2026.04
52.01
2026.04
51.79
2025.10
51.73
2026.01
51.5
2026.01
51.5
2025.10
51.25
2026.01
50.5
2026.02
50.3
2025.10
50.2
Showing 100 of 243 rows