Muse Spark 1.1 Benchmark Scores Revealed

alexandr_wang · x · 2026-07-09

Alexandr Wang noted Muse Spark 1.1 as a competitive agentic and coding model, standing on par with GPT-5.5 and Opus-4.8 in several agentic evaluations.

He also confirmed the model's availability through the new Meta Model API and Meta AI.

Related event: Meta Launches Muse Spark 1.1: A Low-Cost, High-Performance Agentic Model(133 posts)→

Original post →

More from coding & agent

coding & agent channel →