NeoHorse-Jev-4B is now openโa compact model built to turn application states directly into structured decisions and probabilities.
๐ค
๐ Scores 77.70 across six text decision benchmark groups, ranking first among the four open-weight models with complete results in the comparison.
โก Prefill-only inference avoids autoregressive answer generation and supports three decision primitives: Choice for action selection, Noul for yes/no judgment, and Score for ordered ratings.
๐ฎ The same interface can power request routing, tool selection, workflow control, games, robot manipulation, and autonomous-driving simulations.
๐ผ๏ธ Supports text inputs or a single image combined with text, returning normalized probabilities that applications can use directly.
๐ ๏ธ Deploy locally through vLLM, SGLang, Python, CLI, or HTTP. Apache 2.0.