← All projects
better-jev-bench
asp616848/better-jev-bench Apache-2.0 Python Eval & Align
rank#338
A wide, multi-domain, multi-modal decision/classification benchmark corpus, built in the Jev typed-decision style — for training and evaluating System One models
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last push
- today
Star history starts building from the first daily refresh.