Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
multi-hop deep search on BrowseComp-Plus
Loading...
36.17
Pass@1 Accuracy
Self-Manager
4.086
12.4155
20.745
29.0745
Jan 25, 2026
Pass@1 Accuracy
Recall
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
Recall
Self-Manager
Backbone=Qwen3-30B-A3B...
2026.01
36.17
45.39
FoldAgent
Backbone=Qwen3-30B-A3B...
2026.01
35.65
43.04
ReSum
Backbone=Qwen3-30B-A3B...
2026.01
31.24
38.9
ReAct
Backbone=Qwen3-30B-A3B...
2026.01
28.47
37.33
Qwen3-30B-A3B
Category=LLMs w/ Searc...
2026.01
5.32
6.7
Feedback
Search any
task
Search any
task