EgoPoint-Bench - Simulation Function & State: 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 Function & State questions (function and state) among the 1,929 simulation test questions. Accuracy in percent; higher is better.

Metric: Accuracy (%) on the Function & State questions among the 1,929 held-out simulation test questions (HM3D, HSSD and AI2-THOR scenes); 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 2031. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5 Mini58.22#364
2InternVL3.5-2B-Instruct55.14#6517
3Qwen 3 VL 8B Instruct54#1029
4Qwen 3 VL 32B Instruct53.75#606
5Gemini 3 Flash53.33#175
6InternVL3.5-8B-Instruct52.5#1891
7Gemini 3 Pro51.39#145
8InternVL3.5-14B-Instruct51.14#1736
9GLM-4.6V-Flash50.81#1040
10GPT-5.2 Instant49.81#304
11LLaVA-v1.5-7B46.89#7630
12LLaVA-NeXT-7B45.42#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-function-state · How It Works · Data refreshed daily, snapshot 2026-11-21.