Zero-shot benchmark: Laya's advertised win over Jev does not reproduce on four datasets
A frozen-protocol comparison of Jev 1.13, PrismNLI-0.4B and Laya with raw predictions, calibration and latency published. Laya ties Jev on the emotion dataset and trails it by 10 to 33 points elsewhere.

- Launch
- Laya
- Use case
- Research
- Format
- Repo
- Source
- github.com
Camilo
Dynamic Machine Learning practitioner and Software Developer with transferrable skills in Deep learning.



