PersonalHomeBench - Counterfactual Reasoning (Sole Reasoning): leaderboard
PersonalHomeBench (2026) tests models as assistants in generated, persona-rich smart homes. Counterfactual reasoning asks paired questions whose hypothetical change does or does not alter the answer; accuracy in percent, with the full household context in the prompt and no tools. Higher is better.
Metric: Accuracy (%) on 2,000 counterfactual questions, macro-averaged over the variants that change and that keep the ground-truth answer (exact match, else a Gemini 2.5 Pro semantic-equivalence judge), 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 February 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3 30B | Thinking | 74.53 | |
| 2 | GPT-OSS-20B | High | 74 | #1183 |
| 3 | GPT-4 | 73.45 | #970 | |
| 4 | GPT-4o | 71.3 | #751 | |
| 5 | Qwen 3 4B | Reasoning | 71 | #2348 |
| 6 | nemotron-3-nano-30B-a3B | 70.83 | #1946 | |
| 7 | Qwen 3 30B Instruct | 63.55 | #1365 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=personalhomebench-counterfactual-reasoning-sole-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.