A continuously updated benchmark evaluating AI coding agents on real-world software engineering tasks from GitHub issues.
Unipat AI
UnipatAI
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
ClawBench: Can AI Agents Complete Everyday Online Tasks? updated a dataset 10 days ago
UnipatAI/Monthly-SWEBench-2026-03 published a dataset 14 days ago
UnipatAI/Monthly-SWEBench-2026-03Organizations
None yet