Official benchmarks map / VDEBench
sensenova/SenseNova-U1.5-8B-MoT is ranked first on the VDEBench leaderboard with 0.83, 2.7% ahead of Qwen/Qwen-Image-2.1. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | sensenova/SenseNova-U1.5-8B-MoT | sensenova | 0.83 |
| 2 | Qwen/Qwen-Image-2.1 | Qwen | 0.81 |
| 3 | black-forest-labs/FLUX.2-klein-4B | black-forest-labs | 0.77 |
| 4 | Qwen/Qwen-Image-Edit | Qwen | 0.76 |
| 5 | meituan-longcat/LongCat-Image-Edit | meituan-longcat | 0.7 |
| 6 | FireRedTeam/FireRed-Image-Edit-1.0 | FireRedTeam | 0.69 |
| 7 | Qwen/Qwen-Image-Edit-2511 | Qwen | 0.66 |
| 8 | stepfun-ai/Step1X-Edit-v1p2 | stepfun-ai | 0.64 |
| 9 | FireRedTeam/FireRed-Image-Edit-1.1 | FireRedTeam | 0.64 |
| 10 | meituan-longcat/LongCat-Image-Edit-Turbo | meituan-longcat | 0.63 |
VDEBench is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.
Original board: huggingface.co/datasets/hongzhuyi/VDEBench
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.