UniPat AI

Popular repositories Loading

1. BabyVision BabyVision Public

   We introduce BabyVision, a benchmark revealing the infancy of AI vision.

   Python 254 10

2. SWE-Vision SWE-Vision Public

   Python 175 8

3. UniScientist UniScientist Public

   UniScientist is designed to advance universal scientific research intelligence through a unified paradigm

   Python 172 13

4. SaaS-Bench SaaS-Bench Public

   Official repository for SaaS-Bench: realistic, locally deployable SaaS workflows for GUI agent evaluation.

   Python 98 13

5. EvoCodeBench EvoCodeBench Public

   Python 28

6. RoadmapBench RoadmapBench Public

   Evaluating Long-Horizon Agentic Software Development Across Version Upgrades — 115 tasks, 17 repos, 5 languages

   Python 16