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

Multi-turn Agentic Tool-use on TauBench-Airline (OOD)

35.5Success Rate (SR)

HERO

7.4214.712229.29Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
35.511.2
2026.06
33.511.6
2026.06
3212.6
2026.06
3012.3
2026.06
2613.4
2026.06
19.510.1
2026.06
1814
2026.06
12.513.7
2026.06
1213.1
2026.06
8.513.9