Perplexity open-sources Decider v1.3 models, gaining 6.54 points on 63 production classification tasks
AravSrinivas · x · 2026-11-13
Perplexity CEO AravSrinivas announced open-sourcing Decider v1.3 and Decider Flash v1.3, with weights on Hugging Face and free access on OpenRouter for a week.
The new v1.3 capability is "locate": describe what to find and the model returns matching text with character offsets, enabling batch-mode decision plus evidence/entity extraction. Across 17 out-of-domain NER, PII and extractive QA tasks, Decider significantly outperforms the best general extraction model, and on 63 of Perplexity's production classification tasks v1.3 is 6.54 points more accurate than the classifiers currently in production. Shopify CEO Tobi Lütke endorsed it as a "Great model".
Related event: Perplexity Open-Sources Decider v1.3 Decision Models(15 posts)→
More from Models
- Cloudflare hosts Thinking Machines' inkling 2 small on Workers AI at day-0 speed — michellechen · 2026-11-14
- Masked decoding trick tames text rivers in Gemma 3 12B, with a width-aware LoRA and coherence RL — cephaloform · 2026-11-14
- 250,000-human AI mafia game finds OpenAI models lie most, Anthropic snitches — Scobleizer · 2026-11-14
- Developer downgrades Claude Ultra to Pro and moves all work to Codex over 5-hour rate limits — umeshonai · 2026-11-14
- Pangram details per-domain false positive rates (1 in 10,000), enabling profitable AI detection — soldni · 2026-11-14
- Blogger predicts GPT-6.2 launches before Nov 19, floats three reasons for the delay — kimmonismus · 2026-11-14