Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Task Completion on τ2-bench Retail
Loading...
100
Success Rate
RAC
89.6
92.3
95
97.7
May 5, 2026
Success Rate
Completion Rate
Time (s)
Token Usage (k)
Updated 2mo ago
Evaluation Results
Method
Method
Links
Success Rate
Completion Rate
Time (s)
Token Usage (k)
RAC
Framework=RAC
2026.05
100
89
22
66,000
SagaLLM
Framework=SagaLLM
2026.05
98
-
65
71,000
LangGraph
Framework=LG(PE), Prom...
2026.05
91
-
30
52,000
LangGraph
Framework=LG
2026.05
90
-
28
49,000
Feedback
Search any
task
Search any
task
