TauBench V3 Airline

τ-bench Retail simulates a customer-service agent in a retail business. The model talks to a simulated user and must use the company's tools (orders, refunds, policy rules) to actually solve the customer's problem. Only when the database state ends up exactly right does the task count as solved.

TauBench V3 Airline measures how well a model acts as a general-purpose agent. In detail, it checks:

• calling tools with correct arguments
• following written policies while serving the simulated customer
• multi-turn conversation behaviour (asking, confirming, acting)
• correct final database results, not just polite replies

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

What is the TauBench V3 Airline benchmark?

τ-bench Retail simulates a customer-service agent in a retail business. The model talks to a simulated user and must use the company's tools (orders, refunds, policy rules) to actually solve the customer's problem. Only when the database state ends up exactly right does the task count as solved.

What does TauBench V3 Airline test?

TauBench V3 Airline mainly measures how well a model acts as a general-purpose agent. Concretely, it checks: calling tools with correct arguments; following written policies while serving the simulated customer; multi-turn conversation behaviour (asking, confirming, acting).

How is the TauBench V3 Airline score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get TauBench V3 Airline data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/taubench-v3-airline/scores) or pull it directly from the Open LLM Radar API with any HTTP client.