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

Evidence Retrieval on CORTEXBENCH Comparison

46Hit@5

Gemini 3.1 Pro

23.74429.52235.341.078Jun 29, 2026
Updated 25d ago

Evaluation Results

MethodLinks
4612.6
2026.06
36.633.9
30.545.5
29.835.7
2026.06
29.639.5
29.149.2
28.645.2
24.650.9