A Deep Dive into Decision Models: How Perplexity Decider v1.2 Works

This post dissects Perplexity Decider v1.2, an open decision model built on Qwen-3.8 27B that converts a decoder-only LLM into a non-causal encoder and answers all classification questions in a single prefill step via a 255-option readout head. It covers the /v1/decisions API's yes_no, choice and score question types, training on harmonized datasets such as tasksource with synthetic data and choice shuffling, and post-hoc calibration at temperature T=1.32. The author argues the main case for decision models over autoregressive LLMs is token efficiency, and notes the 9B Decider Flash variant is trained with a distillation loss.