Today for AI
HOT RADAR
llmHEAT 16.2°

AI CURATED HOT STORY · 11/14/2026

Perplexity Open-Sources Decider v1.3 Decision Models with Span Extraction

1 reports archived1 independent sourcesupdated 11/14/2026, 00:13:39
Synthesis & Latest Updates
1 Sources Cross-Validated

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.

LATEST/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.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. Marktechpost (@Marktechpost)T2·71 pts

    Perplexity Open-Sources Decider v1.3 Decision Models with Span Extraction

    • Locate returns exact source spans with start and end character offsets rather than labels alone, while classification still yields probabilities in a single forward pass
    • 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
    • Built on Qwen3.8-27B and Qwen3.5-4B with Apache 2.0 weights; API input pricing is $0.02 and $0.01 per 1M tokens
    • Flash trails Jev 1.14 in finance, programming and law, and all figures are self-reported and need independent verification