# d3-ultra, an open 27B multimodal decision model, ranks #2 on Jev index

> Original title: Meet d3-ultra: our newest open 27B multimodal decision model.

- Source: X search: AI open-source releases
- Published: 2026-10-27T03:01:34.000Z
- Bad Influence: https://badinfluence.news/items/xiy49lnkn5e9ss34ud185do1i
- Original: https://x.com/XunzhuoLiu/status/2114915380926017591

## Summary

The publisher releases d3-ultra, an open 27B multimodal decision model with Apache-2.0 open weights on Hugging Face. It ranks #2 of 230 on the Jev Decision Index text board, 3.03 points above its predecessor d3. The model handles text, images, and video, boxing what it finds and tracking it through time.

## Post

Meet d3-ultra: our newest open 27B multimodal decision model.

#2 of 230 on the Jev Decision Index text board, +3.03 over d3.
Text, images, video: it boxes what it finds and tracks it through time.

Open weights (Apache-2.0): https://huggingface.co/vllm-sr/d3-ultra

#Jev #Decision

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2114915250294358016%2Fimg%2Fuu0ewR_kru3HgLJV.jpg&mode=thumb&exp=1793404800&sig=ca09b7db6fdd6e70)