Jev Decision Index
A decision-model evaluation benchmark published by Jev, comprising separate text and vision leaderboards. It is designed to assess the performance of discriminative and decision models on structured decision-making tasks.
Timeline (last 90 days)
Mammoth-1 is a 27B-parameter model and, according to official information, ranks first on the Jev Decision Index.
The Jev Decision Index and the Artificial Analysis Decision Index are third-party leaderboards designed for decision-type tasks, and their evaluations cover dimensions such as accuracy and consistency in intent classification, entity-extraction-style judgments, and multi-label scoring, rather than generation quality or general knowledge question answering.
Decision 3.0 took first place on both the text and vision leaderboards of the Jev Decision Index.
All Facts (2)
Mammoth-1 is a 27B-parameter model and, according to official information, ranks first on the Jev Decision Index.
50%UnverifiedThe Jev Decision Index and the Artificial Analysis Decision Index are third-party leaderboards designed for decision-type tasks, and their evaluations cover dimensions such as accuracy and consistency in intent classification, entity-extraction-style judgments, and multi-label scoring, rather than generation quality or general knowledge question answering.
50%