精选理由
Moonshot AI 的 Kimi K3 在写作评测上干掉了 Claude Fable 5，成本还低 5 倍，开源模型也能这么强？
Moonshot AI 的 Kimi K3 在内部写作基准中以 2840 Elo 排名第一，超越 Claude Fable 5。相比前代 Kimi K2.6，排名从第 21 跃升至第 1。每个脚本运行成本约 0.25 美元，比被超越的模型便宜 5 倍。这是首个开放权重模型在该基准登顶。
原文 · orange.ai
K3 写作能力超过 Fable5
K3 写作能力超过 Fable5 Louis-François Bouchard 🎥🤖 @Whats_AI Big news from our internal writing benchmark (early results): Kimi K3 by @Kimi_Moonshot is now #1 for writing in our editorial voice, at 2840 Elo, surpassing Claude Fable 5. That is a jump from #21 to #1 over its predecessor, Kimi K2.6. And it runs at about $0.25 per script: 5x cheaper than the model it just displaced at the top. First time an open-weights model tops our board. It surprised us too. More in the replies 👇 🔗 View Quoted Tweet 💬 1 🔄 1 ❤️ 4 👀 1462 📊 1 ⚡