Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web-based Decision-making on τ2 Bench Retail, Telecom, Airline
Loading...
48.3
Retail Score
Imitation Learning
40.5
42.525
44.55
46.575
Feb 5, 2026
Retail Score
Telecom Score
Airline Score
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Retail Score
Telecom Score
Airline Score
Average Score
Imitation Learning
Training Paradigm=Lear...
2026.02
48.3
41.7
38.3
43.7
SR
Training Paradigm=Lear...
2026.02
45
45.8
43.3
45
RWML + Policy RL
Training Paradigm=Self...
2026.02
44.2
45.8
38.3
43.7
IWM
Training Paradigm=Lear...
2026.02
40.8
44.2
46.7
43.3
WM SFT + Policy RL
Training Paradigm=Self...
2026.02
40.8
45
30
40.3
Feedback
Search any
task
Search any
task