精选理由
GLM 5.2 在编码基准上干掉了 GPT-5.5，开源里最强，值得关注。
GLM 5.2 在 FrontierSWE 基准上排名第 3，得分仅次于 Fable 5 和 Opus 4.8，并超越 GPT-5.5。这是首个缩小 Anthropic/OpenAI 与其他提供商之间差距的模型，同时也是目前最强的开源权重模型。该成绩展示了开源模型在编码任务上的竞争力。
原文 · elvis
Looks strong at SWE too. https://t.co/JoYoF22klJ
Looks strong at SWE too. x.com/ProximalHQ/sta… Proximal @ProximalHQ GLM 5.2 ranks #3 on FrontierSWE. It is only behind Fable 5 and Opus 4.8, and it outperforms GPT-5.5. This is the first model that closes the large gap between models from Anthropic / OpenAI and other providers, and it is the strongest open-weight model by far. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 2 👀 238 ⚡