Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Search on xbench DeepSearch
Loading...
61
Accuracy
Solution Aggregation
44.36
48.68
53
57.32
May 30, 2026
Accuracy
Updated 1d ago
Evaluation Results
Method
Method
Links
Accuracy
Solution Aggregation
Model=Gemini-3-flash,...
2026.05
61
FINEVERIFY
Model=Gemini-3-flash,...
2026.05
60
Best-of-N
Model=Gemini-3-flash,...
2026.05
58
Confidence Verify
Model=Gemini-3-flash,...
2026.05
58
Pass@1
Model=Gemini-3-flash,...
2026.05
56
Majority Voting
Model=Gemini-3-flash,...
2026.05
56
Weighted Voting
Model=Gemini-3-flash,...
2026.05
56
FINEVERIFY
Model=GPT-5-mini, Samp...
2026.05
53
Weighted Voting
Model=GPT-5-mini, Samp...
2026.05
52
Best-of-N
Model=GPT-5-mini, Samp...
2026.05
52
Solution Aggregation
Model=GPT-5-mini, Samp...
2026.05
52
Confidence Verify
Model=GPT-5-mini, Samp...
2026.05
49
Majority Voting
Model=GPT-5-mini, Samp...
2026.05
46
Pass@1
Model=GPT-5-mini, Samp...
2026.05
45
Feedback
Search any
task
Search any
task