长周期编码任务,高资源语言(Go、Python)和低资源语言(Ada)
官网在这里:
Epoch AI (https://epoch.ai/MirrorCode)
MirrorCode: What's the largest software project AI can complete on its own? |... (https://epoch.ai/MirrorCode)
MirrorCode is Epoch AI's benchmark for long-horizon coding: AI can reimplement entire programs end-to-end, with no access to the original source code.
关于数据污染:
不理解为什么不放完整排行榜,请Grok帮忙抓出来完整版