PEC-Home (RAG) - Multi-User Level 1: leaderboard

Metric: Execution accuracy (%; 1,068 smart-home commands at ellipsis level 1 of 4 (complete commands), 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
1Qwen 2.5 72B Instruct95.51
2DeepSeek V394.1
3GPT-4o93.07
4Gemma 2 9B (IT)92.6
5Gemma 2 27B (IT)91.95
6Qwen 2.5 7B Instruct91.76
7Qwen 2.5 32B Instruct89.14
8Mistral 7B Instruct (v0.3)88.76
9Qwen 2.5 14B Instruct88.11
10Llama 3.1 8B Instruct73.97

Interactive version: theaggregate.ai/benchmark?slug=pec-home-rag-multi-user-level-1 · How It Works · Data refreshed daily, snapshot 2026-09-26.