Jev 1.13 leads the new Artificial Analysis Decision Index with 58
Claude Haiku 5.5 (Low) scores 61, but one task uses 11 times more time than with Jev 1.13, and the cost is 4.4 times more.
Artificial Analysis made the Decision Index version 1.0. It compares decision models on class, tool calls, knowledge and reasoning. A decision model gives a class and the probability of the class. Jev 1.13 from Typesafe leads with 58. GLiDE from Fastino and Microsoft-Decision-1 from Microsoft score 54. Language models are more accurate, but they cost more and use more time.
Sources
Posted
