Artificial Analysis Decision Index ranks Jev 1.13 first among decision models

Artificial Analysis introduced its Decision Index v1.0, with Jev 1.13 scoring 58, ahead of GLiDE and Microsoft-Decision-1 at 54 each. It says leading decision models perform comparably to language models on classification and tool-calling while responding faster and costing less, but trail them on knowledge and reasoning. Claude Haiku 5.5 (Low) scored 61, though Artificial Analysis measured it at $184 per million tasks and 1.4 seconds per task, versus Jev’s $42 and 0.13 seconds.