EgoPoint-Bench - Simulation: leaderboard
EgoPoint-Bench (2026) asks multimodal models about the object a first-person hand points at, on held-out simulation scenes and real smart-glasses recordings, zero-shot; true/false and single-choice answers by exact match and open answers scored by a GPT-4o judge. This board covers the 1,929 simulation test questions across five capability dimensions. Accuracy in percent; higher is better.
Metric: Accuracy (%) over the 1,929 held-out simulation test questions (HM3D, HSSD and AI2-THOR scenes), all five dimensions; 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 2030. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 58.29 | #1029 |
| 2 | Qwen 3 VL 32B Instruct | 58.28 | #606 |
| 3 | GPT-5 Mini | 57.66 | #364 |
| 4 | Gemini 3 Flash | 57.21 | #175 |
| 5 | Gemini 3 Pro | 56.44 | #145 |
| 6 | GPT-5.2 Instant | 54.8 | #304 |
| 7 | GLM-4.6V-Flash | 53.29 | #1040 |
| 8 | InternVL3.5-8B-Instruct | 52.62 | #1891 |
| 9 | InternVL3.5-2B-Instruct | 51.74 | #6517 |
| 10 | InternVL3.5-14B-Instruct | 49.99 | #1736 |
| 11 | LLaVA-v1.5-7B | 48.82 | #7630 |
| 12 | LLaVA-NeXT-7B | 48.17 | #5032 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=egopoint-bench-simulation · How It Works · Data refreshed daily, snapshot 2026-11-21.