Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

TauBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Customer ServiceTauBench-Telephony (TBTel)
Accuracy90.5
8
Customer ServiceTauBench (TauB)
Accuracy91.8
8
Agentic ReasoningTauBench V2
Airline Score66
3
Agentic ReasoningTauBench Telecom V2
Accuracy42.7
2
Showing 4 of 4 rows