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

Agentic Reasoning on TauBench V2

66Airline Score

Qwen3.5-122B-A10B

48.52853.06457.662.136Apr 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
6662.69574.53
56.2562.8364.3661.15
49.267.86661