DeepSeek 把 V4-Flash 放进 Agent Arena，API 公测也开了，智能体跑分超过 V4-Pro-Preview，还适配 Codex，想试的可以看看。
DeepSeek-V4-Flash 已进入 Agent Arena，将在数百万个真实长程智能体任务中接受评测，任务可调用网页搜索、文件系统和终端工具。官方同步开放 V4-Flash API 公测，称其智能体能力大幅升级，基准得分已明显超过 V4-Pro-Preview。新版 API 原生支持 Responses API 格式，并已适配 Codex。该模型还将在 Frontend Code Arena、Text 和 Vision Arena 中评测，具体分数待公布。
DeepSeek-V4-Flash by @deepseek_ai is in the Arena! In Agent Arena, we measure models on millions of...
DeepSeek-V4-Flash by @deepseek_ai is in the Arena! In Agent Arena, we measure models on millions of real-world, long-horizon agentic tasks from a global community of users. Models can access web search, filesystem, and terminal tools to complete complex workflows. The leaderboard measures model performance on outcomes relative to the average model using a causal tracing methodology. Also available in: Frontend Code Arena, Text, and Vision Arena. Scores coming soon. DeepSeek @deepseek_ai 🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇 🔷 The official V4-Flash now natively supports the Responses API format and is fully adapted for Codex! Check out the configuration details in our official API do api-docs.deepseek.com/quick_start/ag… Meiq 🔗 View Quoted Tweet 💬 9 🔄 3 ❤️ 190 👀 12323 📊 20 ⚡