EgoPoint-Bench - Real-World Function & State: leaderboard
Metric: Accuracy (%) on the Function & State 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 | Gemini 3 Pro | 75.44 |
| 2 | Gemini 3 Flash | 73.98 |
| 3 | GPT-5.2 Instant | 67.49 |
| 4 | GPT-5 Mini | 66.73 |
| 5 | Qwen 3 VL 32B Instruct | 65.03 |
| 6 | Qwen 3 VL 8B Instruct | 58.42 |
Interactive version: theaggregate.ai/benchmark?slug=egopoint-bench-real-world-function-state · How It Works · Data refreshed daily, snapshot 2026-10-07.