SimLife-BP (Language Only, Noiseless Logs) - No Hints: leaderboard
SimLife-BP long-horizon pattern understanding over simulated household life (381 tasks / 1,439 questions), text-only over noiseless ground-truth action logs 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 | Gemma 4 31B (IT) | 67.6 | #178 |
| 2 | Gemma 4 26B A4B (IT) | 64.1 | #293 |
| 3 | Gemini 3 Flash (Preview) | 63.9 | #90 |
| 4 | Gemini 2.5 Flash | 63.7 | #255 |
| 5 | Qwen 3.5 35B A3B | 62.7 | #268 |
| 6 | Qwen 3.5 9B | 56.5 | #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-noiseless-logs-no-hints · How It Works · Data refreshed daily, snapshot 2026-11-05.