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

Science Question Answering on GPQA Diamond

91.9Accuracy

Gemini-3.0

3.676826.580949.48572.3891Jul 14, 2025Sep 2, 2025Oct 23, 2025Dec 13, 2025Feb 1, 2026Mar 24, 2026May 14, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2025.12
91.98,000
2025.12
85.78,000
2025.12
85.716,000
2025.12
84.512,000
2025.12
82.47,000
2026.05
72.695.8
2026.05
69.613.9
2026.05
69.598.6
2025.07
67.51-
2025.08
65.15-
2025.08
64.85-
2025.07
64.81-
2025.07
64.65-
2025.08
64.02-
2025.08
63.61-
2025.08
63.42-
2025.08
61.58-
2025.08
61.11-
2025.08
60.65-
2025.08
60.54-
2026.05
59.113.7
2025.08
58.62-
2025.07
57.24-
2025.08
56.84-
2025.08
56.64-
2026.05
56.686.9
2025.08
56.48-
2025.08
56.23-
2025.08
56.19-
2026.05
54.894.3
2025.08
43.31-
2025.08
43.08-
2025.08
42.8-
2025.07
40.4-
2025.07
40.4-
2025.08
39.11-
2025.08
35.74-
2025.10
33.3-
2025.10
27.7-
2025.10
26.3-
2025.10
26.3-
2025.10
25.8-
2025.10
25.3-
2025.07
24.7-
2025.07
24.2-
2025.10
23.23-
2025.10
23.23-
2025.10
22.7-
2025.10
20.71-
2025.10
20.2-
2025.10
20.2-
2025.10
19.2-
2025.10
19.19-
2025.10
18.7-
2025.10
16.2-
2025.07
13.1-
2025.10
12.1-
2025.10
7.1-
2025.10
7.07-