Meta's Muse Spark 1.3 scores 68 on coding agent index, near Claude Opus 5 at fraction of cost

ArtificialAnlys · x · 2026-09-03

Artificial Analysis benchmarks Meta's Muse Spark 1.3: the max variant (limited preview) scores 68 on the Coding Agent Index in Muse Code, tied with Claude Opus 5 (xhigh) and ahead of Claude Fable 5 (67) and GPT-5.6 Sol (65). The available xhigh variant scores 64 and costs just $1.72 per task — the cheapest above 60 and 1/5 of Opus 5's $8.17. Max averages 14M tokens per task, a third fewer than Opus 5 at the same score.

Related event: Meta launches Muse Spark 1.3, matching Fable 5 at a fraction of the price(53 posts)→

Original post →

More from Models

Models channel →