elvis· @omarsar0 · X·· 2 小时前AI 评分55
AI 导读
Nace 发布多模态决策模型 Drex Max，可直接从截图、录屏、扫描文档、科学图表和照片中做决策，单次决策耗时 34 ms，262K token 场景下低于 1 秒，输入价格 $0.06 / 1M tokens。作者 Elvis Saravia 认为该模型适合 computer-use 和 browser-use 智能体，并引用 Nace 数据称其在 Mind2Web 上得分 88.3%、超过 Jev 1.14，在 Decision Index 上得分 67.6（Jev 1.14 为 60.70）。
正文
Decision models are going multimodal.
Drex Max looks really strong. It can make fast decisions straight from screenshots, screencasts, scanned documents, scientific charts, and photos.
This model is a really good fit for computer-use and browser-use agents, where every step starts with reading the screen.
Nace reports 88.3% on Mind2Web (outperforms Jev 1.14).
Drex Max also scores 67.6 on the Decision Index (Jev 1.14: 60.70).
Drex Max is here: our multimodal decision model text, images, and video 34 ms/decision, under 1s at 262K tokens $0.06 / 1M input tokens available today at https://nace.ai/drex在 X 查看被引用的帖子
来源：elvis · x.com