Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Navigation QA on WebVoyager
Loading...
4.55
Average Action Count
AgentOccam
4.1648
6.7649
9.365
11.9651
Apr 20, 2026
Average Action Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Action Count
AgentOccam
Model=Qwen3, Backbone...
2026.04
4.55
AgentOccam
Model=Qwen3, Backbone...
2026.04
5.34
MANGO
Model=Qwen3, Backbone...
2026.04
5.35
AgentOccam
Model=Qwen3, Backbone...
2026.04
6.07
MANGO
Model=Qwen3, Backbone...
2026.04
6.21
MANGO
Model=Qwen3, Backbone...
2026.04
6.26
AgentOccam
Model=Qwen3, Backbone...
2026.04
6.48
WebWalker
Model=Qwen3, Backbone...
2026.04
7
WebWalker
Model=GPT-5 mini
2026.04
7.38
WebWalker
Model=Qwen3, Backbone...
2026.04
7.44
MANGO
Model=Qwen3, Backbone...
2026.04
7.83
WebWalker
Model=Qwen3, Backbone...
2026.04
9.11
WebWalker
Model=Qwen3, Backbone...
2026.04
9.32
AgentOccam
Model=GPT-5 mini
2026.04
9.46
MANGO
Model=GPT-5 mini
2026.04
14.18
Feedback
Search any
task
Search any
task