PEC-Home (RAG) - Multi-User Level 3: leaderboard

Metric: Execution accuracy (%; 1,068 smart-home commands at ellipsis level 3 of 4 (progressively elliptical), functionally correct device operations; dialogue history retrieved from a vector store, top-3). Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.

Top models

#ModelScore
1DeepSeek V376.78
2GPT-4o76.05
3Qwen 2.5 14B Instruct69.19
4Qwen 2.5 72B Instruct69.1
5Qwen 2.5 32B Instruct68.07
6Qwen 2.5 7B Instruct64.04
7Mistral 7B Instruct (v0.3)63.76
8Gemma 2 27B (IT)62.27
9Llama 3.1 8B Instruct58.71
10Gemma 2 9B (IT)55.24

Interactive version: theaggregate.ai/benchmark?slug=pec-home-rag-multi-user-level-3 · How It Works · Data refreshed daily, snapshot 2026-09-26.