The Agents' Last Exam (ALE) leaderboard lists Muse Spark 1.3 in the second position for agent performance. The AI model held the No. 1 rank on the same benchmark at the time of its initial release before shifting to its current placement.

Alexandr Wang and Yash Var Patel both noted the ranking in recent public comments. The current result confirms the model as the No. 2 performer on the evaluation of AI agents, following its top debut on the leaderboard.