Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Search on GAIA (Pass@1)
Loading...
87.4
Pass@1
Seed1.8
30.5432
45.3041
60.065
74.8259
Dec 28, 2025
Jan 10, 2026
Jan 24, 2026
Feb 7, 2026
Feb 21, 2026
Mar 7, 2026
Mar 21, 2026
Pass@1
Updated 26d ago
Evaluation Results
Method
Method
Links
Pass@1
Seed1.8
2026.03
87.4
GPT-5 High
2026.03
76.7
Gemini 3-pro
2026.03
74.8
Claude-4-Sonnet
2025.12
68.3
Claude Sonnet-4.5
2026.03
66
Gemini 2.5-pro
2026.03
57.3
ASearcher-Web-QwQ
parameters=32B
2025.12
52.8
MiroThinker-8B-DPO-v0.1
parameters=8B
2025.12
46.6
FoldAct-7B
p_drop=0, parameters=7B
2025.12
46.3
FoldAct-7B
p_drop=0.5, parameters=7B
2025.12
45
WebSailor-7B
parameters=7B
2025.12
33
GPT-4.1-mini
2025.12
32.73
Feedback
Search any
task
Search any
task