Perplexity AI has released an updated version of its decision model, pplx-decider-v1.1-27b, which improves the Decision Index score from 56.4 to 61.56, surpassing its predecessor by over 3.5 points. This enhancement is attributed to lifting the causal mask and training on more data, including from tasksource. The model, built on a Qwen3_5Model backbone, requires Python 3.12+, a CUDA GPU with substantial memory, and authenticated Hugging Face access for its private repository. AI
IMPACT Enhances decision-making capabilities for applications requiring nuanced routing or classification.
RANK_REASON This is an update to an existing model, not a novel frontier release.
Read on Hugging Face Trending Models →
- Hugging Face
- Perplexity API
- pplx-decider-v1-27b
- Qwen3.8-27B
- stripe
- CUDA
- DecisionModel
- perplexity-ai/pplx-decider-v1.1-27b
- pplx-decider-v1.1-27b
- Python
- tasksource
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →