TelcoAgent-Bench - Intent Recognition with Intent List (Arabic): leaderboard
Metric: Intent recognition accuracy: mean cosine similarity x100 (-100 to 100, sentence embeddings) between the agent's free-text intent and the gold intent label 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, with the 15-intent list given; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 4B (IT) | 86.4 |
| 2 | Qwen 3 8B | 85.6 |
| 3 | Qwen 2.5 7B Instruct | 83.4 |
| 4 | Granite 3.3 8B Instruct | 79.2 |
| 5 | Llama 3 8B Instruct | 78 |
| 6 | Mistral 7B Instruct | 77.4 |
| 7 | granite-3.1-3B-a800m-instruct | 66.9 |
| 8 | Qwen-7B Chat | 66.2 |
Interactive version: theaggregate.ai/benchmark?slug=telcoagent-bench-intent-recognition-with-intent-list-arabic · How It Works · Data refreshed daily, snapshot 2026-10-07.