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

Stateful Agent-User Interaction on tau-Bench Airline

39.1Pass@1

EVOTOOL

6.96415.30723.6531.993Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
39.1
2026.03
38.8
2026.03
36.8
2026.03
36.7
2026.03
36.3
2026.03
36.2
2026.03
35.9
2026.03
31.3
2026.03
29.9
2026.03
29.2
2026.03
25.3
2026.03
16.4
2026.03
15.7
2026.03
15
2026.03
15
2026.03
14.7
2026.03
14.6
2026.03
14.4
2026.03
11.3
2026.03
10.3
2026.03
8.9
2026.03
8.2