mrconter1/PullRequestBenchmark
Evaluating LLMs performance in PR reviews as an indicator for their capability in creating PRs.
1 best points · 3 comments · 4 Hacker News posts · 13 GitHub stars · View on GitHub
Hacker News discussions
- Towards Complete Automation of SW Development: The PRBenchmark Challenge (1 points, 0 comments, by AIReach, 2024-03-13)
- The PullRequestBenchmark: The Final Countdown to Full Developer Job Automation? (1 points, 3 comments, by AIReach, 2024-03-19)
- PRBenchmark – Expert PR Review Capabilities Equals Expert PR Creation Capability (1 points, 0 comments, by AIReach, 2024-04-05)
- PullRequestBenchmark Challenge: Can AI Replace Your Dev Team? (1 points, 0 comments, by AIReach, 2024-04-10)