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

Science Question Answering on GPQA

87.6pass@1 Accuracy

M2CL

13.96833.08452.271.316Sep 26, 2025Oct 19, 2025Nov 11, 2025Dec 4, 2025Dec 27, 2025Jan 19, 2026Feb 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
87.6
2026.02
78.9
2026.02
76.26
2026.02
74.75
2026.02
73.23
2026.02
73.23
2026.02
72.8
2026.02
72.22
2026.02
71.72
2026.02
71.72
2026.02
71.2
2026.02
70.7
2026.02
70.2
2026.02
66.2
2026.02
66.1
2026.02
65.7
2026.02
65.15
2026.02
65.15
2026.02
64.14
2026.02
62.63
2026.02
62.63
2026.02
62.63
2026.02
62.63
2026.02
62.2
2026.02
62.12
2026.02
61.62
2026.02
61.11
2026.02
59.6
2026.02
59.3
2026.02
58.1
2026.02
57.58
2026.02
57.57
2026.02
54.04
2026.02
53.9
2026.02
53.54
2026.02
53.54
2026.02
53.54
2026.02
52.53
2026.02
52.4
2026.02
52.02
2026.02
52.02
2026.02
51.6
2026.02
49.49
2026.02
46.7
2026.02
46.46
2026.02
46.2
2026.02
45.9
2026.02
43.94
2026.02
43.4
2026.02
39.6
2026.02
39.4
2026.02
38.7
2025.09
38.6
2026.02
37.7
2026.02
37.4
2026.02
36.4
2025.09
36.2
2026.02
35.6
2026.02
35.4
2026.02
35
2026.02
34.9
2026.02
34.5
2026.02
32.8
2026.02
31.9
2026.02
30.8
2025.09
30.6
2026.02
30.3
2025.09
29.2
2026.02
28.7
2026.02
28.7
2025.09
28.6
2025.09
28.4
2026.02
27.6
2026.02
27.5
2025.09
26.4
2025.09
26
2025.09
25.6
2025.09
25.5
2026.02
25
2026.02
24.8
2025.09
24.8
2025.09
23.1
2026.02
21.2
2026.02
20.2
2026.02
16.8