Muse Spark 1.3
Meta · 2 thinking configurations
Intelligence45.1
Input / 1M$1.25
Output / 1M$4.25
Context1M
Tariff: Meta · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost2 measured configurations · 0 without both values
Selected: thinking xhigh · Click a point to switch configuration
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
45.1 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
94.1 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
47.5 %SciCodeCode generation for scientific research problems.
59.7 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
85.4 %MMMU-ProMultimodal understanding of academic problems that include images.
82.0 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
41.5 %Specifications from the catalog
Inputtext, image, video, file
Outputtext
Tool callingYes
Structured outputYes
Speed138.5 tok/s
First token34.90 s
Maximum output943.7K
Catalog listing date2026-09-02