Perplexity Open-Sources Decider v1.3 Decision Models with Span Extraction
Perplexity released Decider v1.3 and Decider Flash v1.3, open-weight decision models that upgrade from label-only classification to returning exact text spans with start and end character offsets via a Locate capability. Across 17 out-of-domain NER, PII and extractive QA tasks, v1.3 averages 69.0 and Flash 63.6, versus 43.3 for Liquid d1 and 33.6 for GLiNER large v2.5; query classification reaches 91.6% over 63 tasks with a 0.27% answer-flip rate. Built on Qwen3.8-27B and Qwen3.5-4B under Apache 2.0, with API input pricing at $0.02 and $0.01 per 1M tokens.
Related Entities
Full Report
▲ Marktechpost AI · 2026-11-13 16
▲ Perplexity just released Decider v1.3 and Decider Flash v1.3, open-weight decision models that now extract exact text spans, not just labels.
The key idea is Locate. You name a field ("location") or write an instruction, and the model returns the matching text with start and end character offsets. A span head plus a LoRA adapter does this while the backbone and decision head stay frozen. Classification questions still return probabilities in 1 forward pass.
On 17 out-of-domain NER, PII and extractive QA tasks, Locate averages 69.0 for v1.3 and 63.6 for Flash, vs 43.3 for Liquid d1 and 33.6 for GLiNER large v2.5. Query classification hits 91.6% across 63 tasks, and the answer-flip rate is 0.27% vs 2.69% to 4.84% for Jev 1.14. It is a trade-off though: Flash trails Jev 1.14 in finance, programming and law, and every number is self-reported.
27B on Qwen3.8-27B, Flash 4B on Qwen3.5-4B, Apache 2.0 weights. API pricing is $0.02 (v1.3) and $0.01 (Flash) per 1M input tokens, with free output......
Full analysis:
