TelcoAgent-Bench - Resolution Accuracy (Arabic): leaderboard
TelcoAgent-Bench (2026) tests small language models as telecom troubleshooting agents: from the first message of an engineer the agent recognizes the intent, calls network tools along a reference path among distractor tools and writes a resolution summary. Resolution accuracy as cosine similarity times 100 between the final summary and the gold summary in Arabic dialogues; higher is better.
Metric: Resolution accuracy: mean cosine similarity x100 (-100 to 100, sentence embeddings) between the agent's final resolution summary and the gold summary 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; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 3 4B (IT) | 84.7 | #4139 |
| 2 | Qwen 3 8B | 82.8 | #1873 |
| 3 | Granite 3.3 8B Instruct | 82.6 | #3866 |
| 4 | Llama 3 8B Instruct | 82.4 | #4852 |
| 5 | Mistral 7B Instruct | 81.7 | #7568 |
| 6 | Qwen 2.5 7B Instruct | 80.6 | #2723 |
| 7 | granite-3.1-3B-a800m-instruct | 78.9 | #8600 |
| 8 | Qwen-7B Chat | 73.3 | #7138 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=telcoagent-bench-resolution-accuracy-arabic · How It Works · Data refreshed daily, snapshot 2026-11-21.