EgoPoint-Bench - Real-World Adversarial Resilience: leaderboard
Metric: Accuracy (%) on the Adversarial Resilience 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 April 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 Instant | 71.27 |
| 2 | Gemini 3 Flash | 63.02 |
| 3 | Gemini 3 Pro | 60.16 |
| 4 | Qwen 3 VL 32B Instruct | 56.83 |
| 5 | Qwen 3 VL 8B Instruct | 53.17 |
| 6 | GPT-5 Mini | 52.38 |
Interactive version: theaggregate.ai/benchmark?slug=egopoint-bench-real-world-adversarial-resilience · How It Works · Data refreshed daily, snapshot 2026-10-07.