Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Deep Research on MuSiQue (MUS) (test)
Loading...
81
Mean Correct Answer Rate
Our best agent
8.616
27.408
46.2
64.992
Oct 17, 2025
Mean Correct Answer Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean Correct Answer Rate
Our best agent
Type=Live web
2025.10
81
WebSailor
Type=Live web
2025.10
69
Our base agent
Type=Live web
2025.10
67
ASearcher
Type=Live web
2025.10
64.9
DeepResearcher
Type=Live web
2025.10
62.78
Search-R1
Type=Static & simulate...
2025.10
61
R1-Searcher
Type=Static & simulate...
2025.10
51.5
ZeroSearch
Type=Static & simulate...
2025.10
11.4
Feedback
Search any
task
Search any
task