EgoPoint-Bench - Real-World Spatial Context: 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 Spatial Context questions (location and reachability) among the 1,162 real-world test questions. Accuracy in percent; higher is better.

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 February 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.2 Instant81.62#304
2Gemini 3 Pro79.06#145
3Gemini 3 Flash78.89#175
4Qwen 3 VL 32B Instruct76.09#606
5Qwen 3 VL 8B Instruct74.55#1029
6InternVL3.5-14B-Instruct72.51#1736
7GPT-5 Mini67.32#364
8GLM-4.6V-Flash67.32#1040
9InternVL3.5-8B-Instruct63.32#1891
10InternVL3.5-2B-Instruct62.55#6517
11LLaVA-v1.5-7B62.13#7630
12LLaVA-NeXT-7B60.09#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-real-world-spatial-context · How It Works · Data refreshed daily, snapshot 2026-11-21.