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

Science Reasoning on GPQA (Pass@1)

70.2Pass@1

SwiR

4.024821.204938.38555.5651Oct 18, 2024Jan 15, 2025Apr 15, 2025Jul 14, 2025Oct 11, 2025Jan 9, 2026Apr 9, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.04
70.2
2026.02
69.7
2026.04
69.7
2026.04
67.17
2026.04
67.17
2026.04
66.16
2026.02
65.7
2026.02
63.64
2026.02
62.63
2026.04
62.63
2026.02
61.65
2026.04
61.62
2026.02
60.01
2026.04
58.08
2026.04
57.58
2026.02
56.36
2026.04
55.05
2026.02
54.6
2026.02
53.7
2026.02
52.4
2026.02
52.08
2026.02
51.61
2026.02
51.39
2026.02
51.39
2026.02
51.3
2026.02
51.2
2026.02
51.07
2026.02
50.7
2026.02
49.1
2026.02
45.2
2026.02
44.2
2026.02
43.1
2026.02
40
2026.04
39.39
2026.04
37.88
2026.04
35.35
2026.02
34.8
2026.04
33.83
2026.04
31.31
2026.02
29.7
2026.02
25.2
2026.02
23
2024.10
17.18
2026.02
16.9
2024.10
13.13
2024.10
11.11
2024.10
10.6
2024.10
10.1
2024.10
9.09
2024.10
6.57