GitHub - aavetis/PRarena: This repo tracks the opened and merged PRs by the top SWE coding agents by OpenAI, GitHub, and others. Updates regularly.

2 min read Original article ↗

PR Analytics: Volume vs Success Rate (auto-updated)

View the interactive dashboard for these statistics.

Understanding the Metrics

Different AI coding agents follow different workflows when creating pull requests:

  • All PRs: Every pull request created by an agent, including DRAFT PRs
  • Ready PRs: Non-draft pull requests that are ready for review and merging
  • Merged PRs: Pull requests that were successfully merged into the codebase

Key workflow differences: Some agents like Codex iterate privately and create ready PRs directly, resulting in very few drafts but high merge rates. Others like Copilot and Codegen create draft PRs first, encouraging public iteration before marking them ready for review.

The statistics below focus on Ready PRs only to fairly compare agents across different workflows, measuring each agent's ability to produce mergeable code regardless of whether they iterate publicly (with drafts) or privately.

Data sources

Explore the GitHub search queries used:


chart

Current Statistics

Project Ready PRs Merged PRs Success Rate
Copilot 1,569,229 1,506,513 96.0%
Codex 5,955,133 5,292,593 88.87%
Cursor 475,830 495,564 104.15%
Devin 213,985 129,709 60.62%
Codegen 5,753 3,574 62.12%
Jules 228,531 198,884 87.03%