Perplexity AI Updates: November 13, 2026
Fully automated. Found, summarized and published by an automated AI pipeline. How posts are labeled
1. Perplexity Releases Decider v1.3 and Decider Flash v1.3 Decision Models Under Apache License, Adding Span Extraction
Perplexity released Decider v1.3 and the distilled Decider Flash v1.3 on November 12, with weights on Hugging Face under an Apache license and access through OpenRouter and the Perplexity Decisions API. The models return probabilities for yes/no, multiple-choice and score questions about a shared text or image input in one forward pass; v1.3 is built on Qwen3.8-27B and Flash on Qwen3.5-4B, and a new locate feature returns matching text spans with character offsets for named entity recognition, PII detection and extractive QA. Perplexity reports 91.6% mean accuracy across 63 internal query classification tasks, a mean nDCG@10 of 83.99 across 72 retrieval tasks (1.81 points above Qwen3-Reranker-8B), and 93.98% agreement with LLM judges on one million sampled Decisions API requests, compared with 93.35% for TypeSafe AI’s Jev 1.14. All figures are Perplexity’s own evaluations, and the post states that Decider Flash v1.3 trails Jev 1.14 in finance, programming and law classification. Source