s1-vision

Model updates models.dev · Pixilabai Source language: Chinese

Excerpt

收录发布日期:2026-10-02(社区数据库,待与官方公告核对)。能力:开放权重;输入:text/image。上下文:16,192 tokens。定位(来源描述):PixilabAI's fast 26B-A4B open-weight decision model on Gemma 4 that returns calibrated probabilities for typed choice, yes/no and score questions about text and images。实际效果:暂无本站独立评测;能力参数不代表评测成绩。资料来自 models.dev 的 Decision Models 目录,厂商目录尚未收录该条目

Short excerpt from the source — open the original for the full text.

Sources

← Back to Daily AI Report