VGenST-Bench - Quantity Change Tracking: leaderboard
Metric: Quantity Change Tracking (figural scale, egocentric, dynamic) accuracy (%) on the base multiple-choice questions of VGenST-Bench under circular evaluation (correct only if right under every cyclic permutation of the options), macro-averaged over the task's QA types, 8 uniformly sampled frames from about 100 synthesized videos per task (generated with text-to-image and image-to-video models from validated scene graphs); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 71.6 |
| 2 | Gemini 3 Flash | 71.4 |
| 3 | GPT-5.4 | 71 |
| 4 | Gemma 4 31B (IT) | 66.9 |
| 5 | Gemma 4 26B A4B (IT) | 61.9 |
| 6 | Qwen 3.5 27B | 57 |
| 7 | Qwen 3.5 9B | 54.4 |
| 8 | Qwen 3.5 4B | 51.6 |
| 9 | GPT-5.4 Nano | 48.2 |
| 10 | GPT-5.4 Mini | 46.3 |
| 11 | Kimi K2.6 | 45 |
Interactive version: theaggregate.ai/benchmark?slug=vgenst-bench-quantity-change-tracking · How It Works · Data refreshed daily, snapshot 2026-10-07.