Add VDEBench evaluation results
#91
by hongzhuyi - opened
This PR adds FLUX.1-Kontext-dev results for VDEBench, evaluated on all 3,506 examples of dense English and Chinese document editing.
| Task | Score ↑ |
|---|---|
| Local (edited region, headline) | 0.423 |
| Global (full page) | 0.321 |
Each score is the equally weighted mean of IoU, CDM, BLEU-4 and TEDS on a 0–1 scale. The result file links to the full metric record from the VDEBench team.