TelcoAgent-Bench - Blueprint Reliability (Arabic): leaderboard
Metric: Blueprint reliability score x100 (0-100) on TelcoAgent-Bench (15 telecom troubleshooting intents, 49 blueprints with 30 sampled dialogues each; the agent starts from the engineer's first message and calls core and distractor network tools), Arabic dialogues: a weighted sum of the exact gold-path rate, the gold-path rate within one edit, and one minus the pairwise edit-distance dispersion across a blueprint's samples (weights not printed; every cell fits 0.5, 0.3 and 0.2); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Granite 3.3 8B Instruct | 46.2 |
| 2 | Qwen 3 8B | 29.3 |
| 3 | Mistral 7B Instruct | 23 |
| 4 | Llama 3 8B Instruct | 19.2 |
| 5 | Gemma 3 4B (IT) | 18.9 |
| 6 | Qwen 2.5 7B Instruct | 17.2 |
| 7 | Qwen-7B Chat | 17.1 |
| 8 | granite-3.1-3B-a800m-instruct | 10.7 |
Interactive version: theaggregate.ai/benchmark?slug=telcoagent-bench-blueprint-reliability-arabic · How It Works · Data refreshed daily, snapshot 2026-10-07.