Best Classification
Classification models that take a state and a set of questions and answer with choices, scores, or probabilities. They skip free-form generation, which keeps them fast and their output easy for software to act on, so they fit routing, ranking, guardrails, and other automation that runs on every request.
Best rated
Laya is an open-weight, non-autoregressive System 1 decision model. Its 421M-parameter English checkpoint pairs a ModernBERT-large encoder with a decision head that evaluates a shared text or JSON state against typed choice, score, and boolean questions in a single forward pass. It returns probabilities and confidence instead of prose, which suits ticket routing, moderation, guardrails, relevance scoring, and other low-latency automation.
Featured Models
Top-performing models in this category, recommended by our community and performance benchmarks.
by TypeSafe AI
Jev is TypeSafe AI's System One decision model for fast, machine-consumable judgments. It evaluates structured or unstructured application state against typed questions and returns bounded choices, ordinal scores, or yes-or-no probabilities with confidence in a parallel pass. Unlike generative language models, Jev does not produce free-form prose; it is designed for routing, classification, ranking, verification, guardrails, and real-time workflows where software must act on predictable outputs.