← All projects
jev-calibration-lab
veermshah/jev-calibration-lab MIT Python Eval & Align
rank#371
Independent calibration benchmark for System One decision models (TypeSafe Jev) vs Claude and a TF-IDF baseline on human-labeled data
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last push
- today
Star history starts building from the first daily refresh.
benchmarkcalibrationllm-evaluationpythonsystem-onetypesafe-jev