EgoMemReason - Activity Pattern Inference: leaderboard
Metric: Accuracy (%; 50 multiple-choice questions). Source: arxiv.org. Saturation forecast: Around 2028. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 48 |
| 2 | Gemini 3 Flash | 44 |
| 3 | Qwen 3 VL 8B | 42 |
| 4 | Molmo2-8B | 22 |
Interactive version: theaggregate.ai/benchmark?slug=egomemreason-activity-pattern-inference · How It Works · Data refreshed daily, snapshot 2026-09-25.