Meta's Muse Spark 1.3 (max) scores 62 on Artificial Analysis Intelligence Index, top-6 of 636

ArtificialAnlys · x · 2026-09-03

Artificial Analysis has published a full evaluation page for Meta's Muse Spark 1.3 (max), a proprietary reasoning model with a 1M-token context window. It scores 62 on the Intelligence Index — well above the class median of 17 — ranking 6th among 636 models.

Notable details: the model was very verbose during evaluation (120M output tokens vs. a 72M median), and pricing currently shows $0.00 per 1M input and output tokens, with speed and cost metrics still unavailable. Full sub-evaluation breakdowns are on the Artificial Analysis Intelligence Index page.

Related event: Meta's Muse Spark 1.3 Beats Sol on Artificial Analysis Leaderboard(2 posts)→

Original post →

More from Models

Models channel →