Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Scientific Question Answering on GPQA Diamond

84.4Accuracy

Gemini 2.5 Pro

1.158422.769244.3865.9908Jan 14, 2026Jan 18, 2026Jan 23, 2026Jan 27, 2026Feb 1, 2026Feb 5, 2026Feb 10, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.02
84.4
2026.02
81.31
2026.02
79.6
2026.02
77.7
2026.02
68.3
2026.02
68.3
2026.02
67.3
2026.02
66.3
2026.02
59.1
2026.02
59.1
2026.02
58.6
2026.02
58.5
2026.02
56.6
2026.02
54.7
2026.02
53
2026.02
53
2026.02
52.7
2026.02
52.5
2026.02
52
2026.02
52
2026.02
51.5
2026.02
49.5
2026.01
47.85
2026.02
47.6
2026.02
47.5
2026.02
46.6
2026.01
46.53
2026.01
46.02
2026.02
44.3
2026.01
43.81
2026.01
37.69
2026.02
37.2
2026.02
36
2026.01
34.91
2026.01
34.34
2026.01
34.15
2026.02
33.5
2026.02
33.2
2026.02
32.7
2026.01
31.69
2026.02
31.3
2026.02
31.3
2026.02
26.8
2026.02
26.8
2026.02
25.5
2026.02
24.6
2026.01
23.61
2026.01
23.3
2026.01
23.17
2026.01
22.85
2026.01
21.72
2026.02
21.4
2026.01
21.4
2026.02
21
2026.01
20.58
2026.01
17.93
2026.01
17.68
2026.01
14.71
2026.01
13.64
2026.01
12.94
2026.01
12.31
2026.01
8.71
2026.01
8.4
2026.01
4.36