Claude Code achieves 84% pull request merge success rate in autonomous deployment study

An academic study on arXiv found that Claude Code achieved an 84 percent success rate on autonomous code deployment pull requests, approaching the human baseline of 85 percent, while Codex achieved 74 percent and Devin scored 43 percent. The study benchmarked agent performance on code commit and merge tasks, with Claude Code the highest-performing tool tested.

Claude Code achieves 84% pull request merge success rate in autonomous deployment study According to an academic study on arXiv, Claude Code achieved an 84 percent success rate on autonomous code deployment pull requests, approaching the human baseline of 85 percent. Codex achieved 74 percent, while Devin scored 43 percent. The study benchmarked agent performance on code commit and merge tasks, with Claude Code the highest-performing tool tested. Topics Sources - Official Read article https://arxiv.org/abs/2607.21832 This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.