Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Evidence Retrieval on CORTEXBENCH Bridge
Loading...
38.4
Hit@5
Gemini 3.1 Pro
19.576
24.463
29.35
34.237
Jun 29, 2026
Hit@5
Hit@15
Updated 25d ago
Evaluation Results
Method
Method
Links
Hit@5
Hit@15
Gemini 3.1 Pro
2026.06
38.4
14.1
GPT-4o
2026.06
33.4
27.9
GPT-5.4
2026.06
24.4
28.6
DeepSeek-V4-Flash
2026.06
23.1
31.6
DeepSeek-V3.2
2026.06
22.7
31.4
Gemini 3 Pro
2026.06
22.5
55
Claude Opus 4.6
2026.06
20.6
40.8
Claude Sonnet 4.6
2026.06
20.3
41.1
Feedback
Search any
task
Search any
task