@omarsar0· @omarsar0 · X·· 2026-08-21精选AI 评分67
AI 导读
DeepSeek-V4-Flash-Vision-Exp 已在 DeepSeek API 平台上线，该实验性多模态模型在文本能力上与 DeepSeek-V4-Flash 持平，在多模态智能体基准上大幅超越 V4-Flash 并接近 Opus-4.8。DeepSeek Harness 0.1.1 同日发布，内置对新模型的直接支持，调用模型名为 deepseek-v4-flash-vision-exp。作者另提示关注支持文本、图像和视频输入的 Ox Alpha 1M token 上下文，称其在编码和智能体任务上表现突出。
推荐理由
官方基准对比显示该实验模型在多模态智能体任务上接近 Opus-4.8，读者可据此了解多模态智能体的当前水平。
正文
Brace yourselves. We just entered a new era of frontier multimodal models.
DeepSeek-V4-Flash-Vision-Exp advances multimodal agent performance.
Also, pay attention to Ox Alpha 1M token contexts with text, image, and video inputs, excelling in coding and agentic tasks. https://t.co/MMLX86hhtq
DeepSeek-V4-Flash-Vision-Exp is now live on the DeepSeek API Platform! 🚀 🔹 This experimental multimodal model matches DeepSeek-V4-Flash on text capabilities—including agents, reasoning, and world knowledge. 🔹 On multimodal agent benchmarks, V4-Flash-Vision-Exp makes a major leap over V4-Flash, bringing multimodal agent performance close to Opus-4.8. Try it with model='deepseek-v4-flash-vision-exp'. DeepSeek Harness 0.1.1 was released today with out-of-the-box support for the new model. 1/n在 X 查看被引用的帖子
来源：@omarsar0 · x.com