Perplexity pplx-decider-v1-27b
Open-weight 27B decision model fine-tuned from Qwen3.8-27B for classification and judgment tasks, plus a new Decisions API at $0.04 per million input tokens with free output tokens.
Why it matters
Open decision model that beats its own base by 11 points on average across 11 benchmarks (incl. 88.8% on RAGTruth hallucination detection) — cheap, calibrated judgments instead of a frontier model for every gating call.
What you could build with it
A customer-support platform could route tickets, detect prompt injection, and verify RAG answers with calibrated probability scores, using cheap 27B inference instead of a frontier model for every judgment call.
Does it hold up?
Too early to judge — the model card reports 85.71% average across 11 benchmarks vs 74.76% for the Qwen3.8-27B base, but no independent community evaluations yet.
Built with Perplexity pplx-decider-v1-27b
- Perplexity Releases Pplx-decider-v1-27b for Advanced Text Classification and Decision-Makingarticle · Hands-on breakdown of the 11-benchmark results and enterprise use cases: ticket routing, RAG validation loops, compliance auditing.
Learn more
First spotted on hf: source.
More AI models
ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.