Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Navigation on WebArena Nav
Loading...
54
Execution Success Rate
GPT-5
6.16
18.58
31
43.42
Apr 22, 2026
Execution Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Execution Success Rate
GPT-5
Method=Few-Shot, Avg L...
2026.04
54
Meta-Tool (3B)
Method=Ours, Avg Laten...
2026.04
32
Llama-3.2-3B-Ins.
Method=Few-Shot, Avg L...
2026.04
28
AgentLM-7B
Method=Few-Shot, Avg L...
2026.04
8
Feedback
Search any
task
Search any
task