Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Browsing/Site Navigation on AgentBench WS
Loading...
52
Task Completion Score (TCS)
Gemini-3-flash
31.2
36.6
42
47.4
May 27, 2026
Task Completion Score (TCS)
Updated 6d ago
Evaluation Results
Method
Method
Links
Task Completion Score (TCS)
Gemini-3-flash
Average Steps (Stp)=12...
2026.05
52
Qwen3-235B-A22B
Average Steps (Stp)=4....
2026.05
40.6
GPT-5-mini
Average Steps (Stp)=16...
2026.05
40.4
DeepSeek-V3.2
Average Steps (Stp)=16...
2026.05
32
Feedback
Search any
task
Search any
task