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

Conversational Agent Evaluation on tau2 Airline (Success Rate)

78Success Rate

Pass@N (oracle)

2639.55366.5Jun 24, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
78
2026.06
72
2026.06
72
2026.06
64.8
2026.06
64
2026.06
64
2026.06
64
2026.06
62
2026.06
60
2026.06
58
2026.06
58
2026.06
48
2026.06
36
2026.06
34.5
2026.06
34
2026.06
34
2026.06
30
2026.06
28
2026.06
28
2026.06
28