E3VS-Bench - Counting: leaderboard
E3VS-Bench (2026) embodied active-perception episodes on Counting questions (instances of an object class across the scene): a vision-language agent moves a 5-DoF camera in 3D Gaussian Splatting scenes, and a GPT-5.1 answerer and judge score the outcome 5 (correct) or 1 (incorrect). Mean score on a 1-5 scale; higher is better.
Metric: Judge score on Counting questions (instances of an object class across the scene) of the E3VS-Bench test split (377 episodes, 21 3D Gaussian Splatting scenes): the model drives a 5-DoF camera agent (at most 25 steps) to a viewpoint from which the question can be answered; GPT-5.1 then answers from the agent's final view and a GPT-5.1 judge scores the answer 5 (correct) or 1 (incorrect); mean judge score on a 1-5 scale; higher is better. Source: arxiv.org. Saturation forecast: Around January 2028. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 2.5 Pro | 2.04 | #276 | |
| 2 | Gemini 3 Pro | 1.96 | #145 | |
| 3 | Qwen 3 VL 8B | 1.96 | #917 | |
| 4 | GPT-5.1 | Non-reasoning | 1.88 | #240 |
| 5 | Gemini 3 Flash | Non-reasoning | 1.88 | #175 |
| 6 | Qwen 3 VL 30B A3B | 1.84 | #784 | |
| 7 | Step3 VL 10B | 1.64 | #1080 | |
| 8 | InternVL3.5-8B | 1.6 | #1604 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=e3vs-bench-counting · How It Works · Data refreshed daily, snapshot 2026-11-21.