NumerosityVLM: leaderboard
Metric: Exact-match accuracy (%; the model picks the object count from 12 options, 1 to 100 on a logarithmic grid, across 10,800 synthetic images in six controlled conditions; zero-shot, closed-ended prompt; chance is 8.3). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 83.97 |
| 2 | Qwen 3 VL 4B Instruct | 77.73 |
| 3 | InternVL3-8B | 77.21 |
Interactive version: theaggregate.ai/benchmark?slug=numerosityvlm · How It Works · Data refreshed daily, snapshot 2026-09-29.