Meta · Released 2026-10-15

Muse Spark Open

816B total parameters and 42B active, with text, image, audio and video inputs and text output. Self-host under the Muse Model License; published quantized examples still occupy hundreds of GB of memory. AA at xhigh scores 39, separately from Spark 1.3 and Wonder.

Original model explanation ↗

Where it stands in the leaderboard

Artificial Analysis intelligence comparison

39points

Intelligence Index

Rank 23 among included models

Test configuration: xhigh

Source read · · v4.3.2

Each model uses its highest tested setting, with fallback conditions retained. Original K3 remains at max44 from its readable individual page; the aggregate page now lists K3.1 Pro separately. Scores use one evaluator. The index mainly evaluates English text tasks; examine Chinese and image capabilities separately.

Source evaluation & rankings ↗

Evaluations: conditions and results

Meta model evolution

  1. Muse Spark 1.1 → 1.2

    Coding, debugging and codebase understanding advance through co-training with Muse Code; the model and terminal agent launch together as distinct layers.

    Original release ↗
  2. Muse Spark 1.2 → 1.3

    The release emphasizes longer tasks, tool use and coding, with max effort available in Muse Code and Meta Model API.

    Original release ↗
  3. Muse Wonder / Muse Wonder Full · 首次发布

    The new series emphasizes Active Memory, Active Focus, long-running tasks and coding. Wonder opens through Meta Model API and Muse Code; Full is for Muse Code subscribers. Personal Muse integration remains a later rollout.

    Original release ↗
  4. Muse Spark Open · 权重发布

    The 816B-total, 42B-active multimodal model releases weights under the Muse Model License. It derives from August’s Spark with additional safety post-training, rather than the same weights as Spark 1.3 or Wonder.

    Original release ↗