PEC-Home (RAG) - Dynamic Preferences Level 3: leaderboard

Metric: Execution accuracy (%; 712 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 V362.08
2GPT-4o61.24
3Qwen 2.5 32B Instruct58.43
4Gemma 2 27B (IT)57.87
5Qwen 2.5 72B Instruct54.49
6Qwen 2.5 7B Instruct52.67
7Qwen 2.5 14B Instruct47.33
8Mistral 7B Instruct (v0.3)44.24
9Gemma 2 9B (IT)42.42
10Llama 3.1 8B Instruct35.67

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