LaunchAI ModelsOctober 6, 2026

Perplexity's pplx-decider-v1.1-27b tops Decision Bench at 94.5% accuracy

Read original source →huggingface.co

The open-weights multimodal decision model hit 94.5% accuracy across 1,071 cases at $0.017 per 1,000 decisions, per Perplexity. It returns typed probabilistic answers — yes/no, choice, or rubric score — for up to 128 questions per request, and is now on OpenRouter at $0.02/M input with free output.

How this story unfolded

2 days · 1 report · 3 community posts · from Oct 7

  1. Oct 7
  2. Oct 9

More stories today

Open the live feed