Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Search on HLE text-only
Loading...
45.8
Pass@1
Gemini 3-pro
18.76
25.78
32.8
39.82
Mar 21, 2026
Pass@1
Updated 25d ago
Evaluation Results
Method
Method
Links
Pass@1
Gemini 3-pro
evaluation_set=full set
2026.03
45.8
GPT-5 High
2026.03
41.7
Seed1.8
2026.03
40.9
Claude Sonnet-4.5
2026.03
32
Gemini 2.5-pro
2026.03
19.8
Feedback
Search any
task
Search any
task