Perplexity releases Decider v1.3 with text span locatingMachine translation
Perplexity 发布 Decider v1.3,新增文本片段定位功能
Perplexity has released Decider v1.3 and Flash v1.3. The models return option probabilities for questions about text or images, while the new Locate feature extracts text spans and character offsets. Their weights are available under Apache 2.0, and both models run through the Decisions API and OpenRouter. The reported benchmark results are self-reported by Perplexity and have not been independently verified here.
This source permits summary display only.
Read at the original source