Muse Spark 1.2
Meta · 1 configuration
Intelligence39.6
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 cost1 measured configurations · 0 without both values
Selected: thinking xhigh · Click a point to switch configuration
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
39.6 pointsDeepSWE · pass@1Software-engineering tasks on mini-swe-agent v1.1. Pass@1 across evaluated runs, with measured cost per task. The 95% intervals may overlap.
54.9 % ±2.1GPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
90.4 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
45.5 %SciCodeCode generation for scientific research problems.
57.4 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
80.1 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
45.4 %Specifications from the catalog
Inputtext, image, video, file
Outputtext
Tool callingYes
Structured outputYes
Speed226.0 tok/s
First token11.70 s
Maximum output943.7K
Catalog listing date2026-08-05
DeepSWE v1.1 · 113 tasks · mini-swe-agent · cost $3.70 / task · 101 mean steps · 99.2K mean output tokens. Published by the source 9/22/2026.