PersonalHomeBench - Feature Recommendation (Sole Reasoning): leaderboard

PersonalHomeBench (2026) tests models as assistants in generated, persona-rich smart homes. Feature recommendation ranks appliance features by their relevance to the situation; MAP@1 times 100, with the full household context in the prompt and no tools. Higher is better.

Metric: MAP@1 (times 100) on 1,000 feature recommendation tasks (rank appliance features from API-level inventories by contextual relevance), over the text-based split of PersonalHomeBench (1,100 generated, manually reviewed households with persona-based occupants and appliances), temperature 0, in the sole-reasoning setting (no tools; the full household context, occupant profiles and memories are given in the prompt); each model at its stated reasoning mode; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-4o27.7#751
2GPT-427#970
3Qwen 3 30B Instruct26#1365
4nemotron-3-nano-30B-a3B25.9#1946
5Qwen 3 4BNon-reasoning25.8#2348
6Qwen 3 30BThinking25.4
7GPT-OSS-20BHigh24.7#1183

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=personalhomebench-feature-recommendation-sole-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.