EgoPoint-Bench: leaderboard
Metric: Accuracy (%) over all 3,091 test questions (simulation and real-world, item-weighted) about the object a first-person hand points at; 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 February 2028. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 62.71 |
| 2 | Gemini 3 Pro | 62.29 |
| 3 | Qwen 3 VL 32B Instruct | 60.54 |
| 4 | GPT-5.2 Instant | 59.29 |
| 5 | GPT-5 Mini | 58.75 |
| 6 | Qwen 3 VL 8B Instruct | 58.23 |
Interactive version: theaggregate.ai/benchmark?slug=egopoint-bench · How It Works · Data refreshed daily, snapshot 2026-10-07.