EgoPoint-Bench - Real-World Spatial Context: leaderboard
Metric: Accuracy (%) on the Spatial Context questions among the 1,162 real-world smart-glasses test questions; zero-shot (direct inference); true/false and single-choice questions by exact match, open-ended answers scored 0 to 1 by a GPT-4o judge; greedy decoding for open models, temperature 0 for API models; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 Instant | 81.62 |
| 2 | Gemini 3 Pro | 79.06 |
| 3 | Gemini 3 Flash | 78.89 |
| 4 | Qwen 3 VL 32B Instruct | 76.09 |
| 5 | Qwen 3 VL 8B Instruct | 74.55 |
| 6 | GPT-5 Mini | 67.32 |
Interactive version: theaggregate.ai/benchmark?slug=egopoint-bench-real-world-spatial-context · How It Works · Data refreshed daily, snapshot 2026-10-07.