谷歌新出的Gemini 3.7 Flash在智能体评测里冲到第20，比上代强一截，编码和网页开发更好用了，感兴趣的可以试试。
Google DeepMind的Gemini 3.7 Flash (High)在Agent Arena取得+3.4%净提升。整体排名第20，高于Gemini 3.6 Flash (High)的第35名。长程智能体任务表现与Claude Sonnet 4.6和GPT-5.6 Terra (xHigh)处于同一区间。其Confirmed Success信号得分提升10%，位列第5。官方称该模型在编码、知识工作和网页开发方面更强。
Gemini 3.7 Flash (High) by @GoogleDeepMind has landed in the Agent Arena with net-improvement score ...
Gemini 3.7 Flash (High) by @GoogleDeepMind has landed in the Agent Arena with net-improvement score of +3.4%! It ranks #20 overall in Agent Arena — a significant jump over Gemini 3.6 Flash (High) at #35 , and now sits in the same range as Claude Sonnet 4.6 and GPT-5.6 Terra (xHigh) for long-horizon agentic tasks. By signal, Gemini 3.7 Flash (High) scored high in Confirmed Success with +10%, ranked #5 . Congrats to the @GoogleDeepMind team on this release! Google DeepMind @GoogleDeepMind Gemini 3.7 Flash is here. It’s stronger for coding, knowledge work, and web development. 🧵 🔗 View Quoted Tweet 💬 7 🔄 4 ❤️ 79 👀 6971 📊 11 ⚡