Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Browsing Research on BrowseComp (BC)
Loading...
67.8
Pass@3
Claude Opus 4.5
13.98
27.9525
41.925
55.8975
Mar 7, 2026
Mar 19, 2026
Apr 1, 2026
Apr 14, 2026
Apr 26, 2026
May 9, 2026
May 22, 2026
Pass@3
Updated 8d ago
Evaluation Results
Method
Method
Links
Pass@3
Claude Opus 4.5
Model Category=Frontie...
2026.05
67.8
Quest-35B
Model Category=Open-We...
2026.05
64.6
GPT-5
Model Category=Frontie...
2026.05
59.9
Gemini 3 Pro
Model Category=Frontie...
2026.05
59.2
OpenAI-DR
Model Category=Frontie...
2026.05
51.5
Quest-35B
Model Category=Open-We...
2026.05
45.5
Tongyi-DR
Model Category=Open-We...
2026.05
43.4
Quest-30B
Model Category=Open-We...
2026.05
37
WeDAS
Model=Miro-30B
2026.03
35
MiroFlow
Model=Miro-30B
2026.03
33
WeDAS
Model=GPT-5-MINI
2026.03
30
MiroFlow
Model=GPT-5-MINI
2026.03
29
OpenResearcher
Model Category=Open-We...
2026.05
26.3
WebSailor
Model=WebSailor-72B
2026.03
18.96
WebSailor
Model=WebSailor-32B
2026.03
16.05
Feedback
Search any
task
Search any
task