DVBench - Animation: leaderboard
Metric: Accuracy (%). Source: bomiaowang.github.io. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.5 | 72.18 |
| 2 | Gemini 3.1 Pro (Preview) | 69.92 |
| 3 | Claude Sonnet 4.6 | 68.42 |
| 4 | GPT-5.4 | 63.91 |
| 5 | Qwen 3.5 397B A17B | 62.41 |
| 6 | Qwen 3.5 27B | 59.4 |
| 7 | Qwen 3.5 122B A10B | 58.65 |
| 8 | Gemma 4 31B (IT) | 57.89 |
| 9 | Qwen 3.5 9B | 54.89 |
Interactive version: theaggregate.ai/benchmark?slug=dvbench-animation · How It Works · Data refreshed daily, snapshot 2026-09-19.