Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool-use Task Completion on Tau2-Bench Telecom subset Solo mode
Loading...
43.3
Success Rate
ReAct + EvoSOP
35.084
37.217
39.35
41.483
Jul 8, 2026
Success Rate
Updated 17d ago
Evaluation Results
Method
Method
Links
Success Rate
ReAct + EvoSOP
Backbone=Gemini-3-FP
2026.07
43.3
ReAct + EvoSOP
Backbone=GPT-4o
2026.07
40.9
ReAct + EvoSOP
Backbone=Qwen-Max
2026.07
40.2
ReAct + ASI
Backbone=Qwen-Max
2026.07
39.5
ReAct + ASI
Backbone=GPT-4o
2026.07
37.7
ReAct
Backbone=GPT-4o
2026.07
37.1
ReAct + ASI
Backbone=Gemini-3-FP
2026.07
35.4
Feedback
Search any
task
Search any
task