SmartHome-Bench: leaderboard
Large language model agents are moving beyond text-only interaction toward physical-world control, with smart homes as a representative domain. Real domestic interaction requires understanding ambiguous intents, operating in dynamic environments, and performing multi-turn reasoning. However, existing methods struggle to generate high-quality training data for smart home agents. We propose HomeFlow
Metric: Overall (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 85.8 | #31 |
| 2 | DeepSeek V4 Flash | 85.16 | #137 |
| 3 | GLM-5 | 84.4 | #141 |
| 4 | Qwen 3.5 Plus | 84.15 | #125 |
| 5 | Claude Sonnet 4.6 | 84.09 | #90 |
| 6 | MiniMax-M2.7 | 68.06 | #258 |
| 7 | Qwen 3 8B | 31.87 | #674 |
| 8 | Qwen 3 4B | 30.85 | #829 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=smarthome-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.