AI Tools & Models HOTFeaturedAll
arXiv cs.AIScore60

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Summary

BigCodeArena borrows the crowdsourced evaluation idea of Chatbot Arena and uses actual execution results to judge code generation quality, making human-preference evaluation more trustworthy.

Why this matters

Covers model · Relevant to this topic

Open original ↗

Source: arXiv cs.AI · arxiv.org

Topics

Related items