The telecom domain of Tau-Bench as reported in the LLM Benchmark Matrix. Tests AI agents on realistic telecom customer service scenarios requiring tool use and multi-step problem solving.
This definition has not completed editorial and provenance review. Verify its metric, version, source, and evaluation configuration upstream before using it for a model-selection decision.
Domain-specific agentic evaluation with realistic business scenarios.
Matrix snapshot — we also have a dedicated tau-bench scraper. Telecom domain may not generalize.
Higher is better. Task completion rate (0–100%).
Matrix snapshot — we also have a dedicated tau-bench scraper.
| # | Model | Score |
|---|---|---|
| 1 | 100.0 | |
| 2 | 99.9 | |
| 3 | 99.9 | |
| 4 | 99.5 | |
| 5 | 99.5 | |
| 6 | 99.5 | |
| 7 | 99.5 | |
| 8 | 99.5 | |
| 9 | 99.4 | |
| 10 | 99.4 | |
| 11 | 99.4 | |
| 12 | 99.3 | |
| 13 | 99.3 | |
| 14 | 99.3 | |
| 15 | 99.3 | |
| 16 | 99.3 | |
| 17 | 99.2 | |
| 18 | 99.2 | |
| 19 | 99.2 | |
| 20 | 99.2 | |
| 21 | 99.2 | |
| 22 | 99.2 | |
| 23 | 99.1 | |
| 24 | 99.1 | |
| 25 | 99.1 | |
| 26 | 99.1 | |
| 27 | 99.1 | |
| 28 | 99.0 | |
| 29 | 99.0 | |
| 30 | 99.0 | |
| 31 | 99.0 | |
| 32 | 99.0 | |
| 33 | 99.0 | |
| 34 | 99.0 | |
| 35 | 99.0 | |
| 36 | 99.0 | |
| 37 | 99.0 | |
| 38 | 98.9 | |
| 39 | 98.9 | |
| 40 | 98.9 | |
| 41 | 98.9 | |
| 42 | 98.9 | |
| 43 | 98.9 | |
| 44 | 98.8 | |
| 45 | 98.8 | |
| 46 | 98.8 | |
| 47 | 98.8 | |
| 48 | 98.8 | |
| 49 | 98.8 | |
| 50 | 98.8 |