SMH-Bench (Direct Reasoning) - Atomic Control: leaderboard
SMH-Bench (2026) category on single-intent device operations phrased clearly, colloquially or noisily, scored in the executable HomeEnv smart-home simulator. In the Direct Reasoning setting the model sees the full serialized home state and answers once with structured actions that are replayed in the simulator. The board is the success rate in percent; higher is better.
Metric: Success rate (%) on Atomic Control (TC1, 150 single-intent device operations under clear, colloquial or noisy wording); Direct Reasoning: the full serialized home state (rooms, devices, current values, service schemas) and the request in one prompt, one structured JSON answer replayed in the HomeEnv simulator; final home state checked against the goal with untouched devices preserved; clarification and query answers judged by GPT-5; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 95.3 | #94 |
| 2 | Qwen 3.5 397B A17B | 92.7 | #246 |
| 3 | GPT-5.4 | 91.3 | #123 |
| 4 | Claude Sonnet 4.6 | 90.7 | #161 |
| 5 | Claude Haiku 4.5 | 90 | #568 |
| 6 | MiniMax-M2.7 | 81.3 | #518 |
| 7 | GPT-5.4 Mini | 80.7 | #389 |
| 8 | GLM-5 | 80.7 | #260 |
| 9 | DeepSeek V3.2 (Thinking) | 79.3 | #406 (DeepSeek V3.2) |
| 10 | Qwen 3.5 Plus | 79.3 | #232 |
| 11 | Qwen 3.5 9B | 73.3 | #803 |
| 12 | Qwen 3.5 4B | 68.7 | #1175 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=smh-bench-direct-reasoning-atomic-control · How It Works · Data refreshed daily, snapshot 2026-11-13.