Decider v1.3
A specialized model for decision-making and information extraction tasks that supports a natural-language locate capability and returns character offsets; its weights are open-sourced.
Timeline (last 90 days)
Decider v1.3 added the Locate capability, which can be used for text span extraction.
Decider v1.3 reported an average accuracy of 91.6% on 63 query classification tasks.
Perplexity released the Decider V1.2 series of multimodal decision models, including two models, Decider V1.2 27B and Decider Flash V1.2 4B, which are now available on AI Gateway.
All Facts (3)
Decider v1.3 added the Locate capability, which can be used for text span extraction.
50%UnverifiedDecider v1.3 reported an average accuracy of 91.6% on 63 query classification tasks.
50%UnverifiedPerplexity released the Decider V1.2 series of multimodal decision models, including two models, Decider V1.2 27B and Decider Flash V1.2 4B, which are now available on AI Gateway.
50%