TelcoAgent-Bench - Intent Recognition with Intent List (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. Intent recognition with the list of 15 intents given, as cosine similarity times 100 between the stated and gold intent in Arabic dialogues; higher is better.

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. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemma 3 4B (IT)86.4#4139
2Qwen 3 8B85.6#1873
3Qwen 2.5 7B Instruct83.4#2723
4Granite 3.3 8B Instruct79.2#3866
5Llama 3 8B Instruct78#4852
6Mistral 7B Instruct77.4#7568
7granite-3.1-3B-a800m-instruct66.9#8600
8Qwen-7B Chat66.2#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-intent-recognition-with-intent-list-arabic · How It Works · Data refreshed daily, snapshot 2026-11-21.