Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Deep Search on BrowseComp EN
Loading...
67.6
Score
Seed1.8
34.008
42.729
51.45
60.171
Apr 14, 2026
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
Seed1.8
Size=-, Category=Comme...
2026.04
67.6
GPT-5.2 (xhigh)
Size=-, Category=Comme...
2026.04
65.8
GLM-5
Size=744B-A40B, Catego...
2026.04
62
Kimi-K2.5
Size=1T-A32B, Category...
2026.04
60.6
Gemini-3-Pro
Size=-, Category=Comme...
2026.04
59.2
Claude Opus 4.5
Size=-, Category=Comme...
2026.04
57.8
GLM-4.7
Size=355B-A32B, Catego...
2026.04
52
DeepSeek-V3.2
Size=671B-A37B, Catego...
2026.04
51.4
QuarkMedSearch
Size=30B-A3B, Category...
2026.04
47.03
SMTL-100
Size=30B-A3B, Category...
2026.04
43.6
Tongyi DeepResearch
Size=30B-A3B, Category...
2026.04
43.4
Base (Tongyi DeepResearch)†
Size=30B-A3B, Category...
2026.04
42.67
REDSearcher
Size=30B-A3B, Category...
2026.04
42.1
WebResearcher
Size=30B-A3B, Category...
2026.04
37.3
WebSailorV2
Size=30B-A3B, Category...
2026.04
35.3
Feedback
Search any
task
Search any
task