TauBench V2 Telecom

tau2-bench - Telecom domain. Agentic tool use benchmark for telecom customer service scenarios.

Category

General Agents

Max Score

100.0

Score Type

percent

Active

Yes

Model Scores

Scores for TauBench V2 Telecom

Model Score Date Verified
Qwen3-Next-80B-A3B-Thinking
100.00%
10.09.2025 Verified