Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Shopping on AgentBench Web Shopping
Loading...
36.2
Task Completion Score (TCS)
GPT-5-mini
2.712
11.406
20.1
28.794
May 27, 2026
Task Completion Score (TCS)
Updated 6d ago
Evaluation Results
Method
Method
Links
Task Completion Score (TCS)
GPT-5-mini
Average Steps (Stp)=14...
2026.05
36.2
Gemini-3-flash
Average Steps (Stp)=10...
2026.05
26.6
Qwen3-235B-A22B
Average Steps (Stp)=5....
2026.05
10.7
DeepSeek-V3.2
Average Steps (Stp)=19...
2026.05
4
Feedback
Search any
task
Search any
task