MindEdit-Bench - Spatial Editing: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around 2028. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 36.9 |
| 2 | Qwen 3.6 Plus | 35.6 |
| 3 | Claude Opus 4.6 | 28.4 |
| 4 | Seed 2.0 Pro | 27.9 |
| 5 | Qwen 3.5 35B A3B | 20 |
| 6 | Kimi K2.5 | 19.4 |
| 7 | InternVL3-8B | 18.6 |
| 8 | Qwen 3 VL 8B | 15.8 |
| 9 | GPT-5.4 | 15.3 |
| 10 | GLM-4.6V-Flash | 3.5 |
Interactive version: theaggregate.ai/benchmark?slug=mindedit-bench-spatial-editing · How It Works · Data refreshed daily, snapshot 2026-09-25.