Muse Spark 1.1 Shows Significant Evaluation Improvements

alexandr_wang · x · 2026-07-09

The post highlights a leap in JobBench scores from 17 to 54.7 to demonstrate Muse Spark 1.1's substantial performance gains.

This information continues the discussion on the same model's agent task evaluation results, rather than introducing a standalone product or workflow.

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

Original post →

More from Models

Models channel →