Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Autonomous Web Navigation on WebArena-Infinity
Loading...
43.7
Success Rate
Qwen3.5 Plus
14.684
22.217
29.75
37.283
Jun 10, 2026
Success Rate
Average Steps
Teacher Queries per Task
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Average Steps
Teacher Queries per Task
Qwen3.5 Plus
Deployment Mode=teache...
2026.06
43.7
30.49
-
SFT collector with SRC
Deployment Mode=teache...
2026.06
42.5
29.58
12.01
Kimi K2.5
Deployment Mode=teache...
2026.06
39.7
30.2
-
Expert SFT + SRC
Deployment Mode=teache...
2026.06
35
28.1
-
LEAP-style post-hoc correction
Deployment Mode=teache...
2026.06
31.8
27.42
27.42
Expert SFT
Deployment Mode=teache...
2026.06
25.3
12.06
-
OEC-style random switch
Deployment Mode=teache...
2026.06
20.4
17.82
10.09
Base model
Deployment Mode=teache...
2026.06
15.8
29.83
-
Feedback
Search any
task
Search any
task