Replit ⠕· @Replit · X·· 2 小时前AI 评分54
AI 导读
Replit 发布 ViBench 2.0，一个长程软件构建基准：Agent 从空项目开始逐个功能构建完整产品，且无法预知后续需求。最好的模型（GPT-6.1 Sol、GPT-6 Astra、Opus 5.5）也只在 49-65% 的构建中通过全部检查。
正文 · 原文
Today we're releasing ViBench 2.0, a benchmark for long-horizon software building. Agents start from an empty project and build a whole product, one feature at a time, without seeing what comes next.
Even the best models (GPT-6.1 Sol, GPT-6 Astra, Opus 5.5) pass every check in only 49-65% of builds.
ViBench 2.0 is now part of @FireworksAI_HQ’s Specialized Intelligence Index, with official results from Fireworks’ runs.
Read more: https://replit.com/blog/vibench-2-long-horizon-software-benchmark
We’re working to build the largest collection of private and public practitioner evals. Today, 31 new partners join the Specialized Intelligence Index. Compare open, closed, and specialized models on real work, weigh quality against cost, and see where training could pay off. https://fireworks.ai/specialized-intelligence-index/在 X 查看被引用的帖子
来源：Replit ⠕ · x.com