SimLife-BP (Language Only) - No Hints: leaderboard
SimLife-BP long-horizon pattern understanding over simulated household life (381 tasks / 1,439 questions), text-only input, asked with no hints. Question-level accuracy; the input modality is the board. Higher is better. Source: arxiv.org/abs/2609.19610.
Metric: Question-level Accuracy (%). Source: arxiv.org. Saturation forecast: Around February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 66.5 | #90 |
| 2 | Gemini 3.1 Flash Lite | 59.1 | #200 |
| 3 | Qwen 3.5 35B A3B | 58.7 | #268 |
| 4 | Gemini 2.5 Flash | 56.4 | #255 |
| 5 | Gemma 4 26B A4B (IT) | 54.8 | #293 |
| 6 | Qwen 3.5 9B | 54.6 | #391 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=simlife-bp-language-only-no-hints · How It Works · Data refreshed daily, snapshot 2026-11-05.