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

Biomedical Intelligence Evaluation on BixBench 205 (Evaluation)

85.9Accuracy

Gemini 3.1 Pro

2.1823.91545.6567.385May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
85.9
2026.05
69.3
2026.05
53.7
2026.05
50.2
2026.05
49.8
2026.05
48.3
2026.05
42.4
2026.05
42.4
2026.05
42
2026.05
41
2026.05
40.5
2026.05
40
2026.05
38.5
2026.05
38.5
2026.05
35.1
2026.05
30.2
2026.05
26.3
2026.05
23.9
2026.05
22.4
2026.05
20
2026.05
17.1
2026.05
13.2
2026.05
10.7
2026.05
5.4
2026.05
5.4