Perplexity 开源 Decider v1.3 与 Decider Flash v1.3 决策模型并新增 locate 能力
Perplexity 开源决策模型 Decider v1.3 和 Decider Flash v1.3，权重发布在 Hugging Face，并在 OpenRouter 上免费一周。
Aravind Srinivas· @AravSrinivas · X·2026-11-13 07:19· 1 小时前AI 评分55
AI 导读
Perplexity CEO Aravind Srinivas 宣布开源最新决策模型 Decider v1.3 和 Decider Flash v1.3，权重开放在 Hugging Face，并在 OpenRouter 上免费一周。
正文 · 原文
We're open-sourcing our latest versions of Decision Models: Decider v1.3 and Decider Flash v1.3, and making them free on @OpenRouter for a week.
The new capability in v1.3 models is "locate". This lets you describe what to find, and the model returns the matching text with character offsets.
This is useful for batch-mode decision + evidence/entity extraction. On 17 out-of-domain NER, PII and extractive QA tasks, Decider models significantly outperform the best general extraction model.
And, on 63 of our own production classification tasks, v1.3 is 6.54 points more accurate than the classifiers we run today.
Weights are open on Hugging Face: perplexity.ai/hub/blog/perple…
在 X 查看被引用的帖子We're rolling out pplx-decider-v1.3 and pplx-decider-flash-v1.3, the latest version of our open-weight decision models.
v1.3 adds locate, a new feature that extracts spans based on type or instructions.
Now available in our Decisions API, @huggingface, and @OpenRouter.
来源：Aravind Srinivas · x.com
来源：RadarAI · aihot.news