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
Organizations
None yet
datasets 7
UnipatAI/EvoCodeBench
Viewer • Updated • 26 • 587 • 2
UnipatAI/Monthly-SWEBench-2026-05
Viewer • Updated • 100 • 1.51k
UnipatAI/Monthly-SWEBench-2026-03
Viewer • Updated • 112 • 1.38k • 1
UnipatAI/RoadmapBench
Viewer • Updated • 115 • 66.7k • 2
UnipatAI/Monthly-SWEBench-2026-04
Viewer • Updated • 90 • 1.41k
UnipatAI/BabyVision-Gen
Viewer • Updated • 280 • 159 • 2
UnipatAI/BabyVision
Viewer • Updated • 388 • 951 • 15