EgoMemReason - Spatial Preference Inference: leaderboard
Metric: Accuracy (%; 50 multiple-choice questions). Source: arxiv.org. Saturation forecast: Around 2033. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 44 |
| 2 | Gemini 3.1 Pro (Preview) | 40 |
| 3 | Qwen 3 VL 8B | 40 |
| 4 | Molmo2-8B | 34 |
Interactive version: theaggregate.ai/benchmark?slug=egomemreason-spatial-preference-inference · How It Works · Data refreshed daily, snapshot 2026-09-25.