Meta
Muse Spark 1.1
Muse Spark 1.1 is an AI model released by Meta on Thursday, Jul 9 2026, 92 days after Muse Spark. Benchmark results (shown below) cover SWE-Bench Pro, DeepSWE 1.1, Terminal-Bench 2.1, MCP Atlas, JobBench, Toolathlon-Verified, and 10 more.
Benchmarks
Agentic coding
SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better.
61.5%+6.5%vs Muse Spark
Agentic coding
DeepSWE 1.1Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better.
53.3%+43.3%vs Muse Spark
Agentic terminal coding
Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better.
80%+12.7%vs Muse Spark
Multi-step tool use
MCP AtlasCan the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better.
88.1%+5.9%vs Muse Spark
Professional tool use
JobBenchTests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better.
54.7%+37.7%vs Muse Spark
Personal tool use
Toolathlon-VerifiedTests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better.
75.6%+26.2%vs Muse Spark
Multidisciplinary reasoning
Humanity's Last ExamHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better.
62.1%+11.7%vs Muse Spark
with tools
Agentic computer use
OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better.
80.8%+27.5%vs Muse Spark
Agentic financial analysis
Finance Agent v2Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better.
57.2%
Agentic legal work
Harvey's Legal Agent BenchmarkHarvey's test of whether an AI agent can complete real legal work — drafting and reviewing documents, working with spreadsheets and presentations, and navigating files the way a lawyer's assistant would. Higher is better.
20%
Tax questions
TaxEval v2A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better.
79.72%
Medical admin work
MedScribeCan the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better.
88.89%
Chart reasoning
CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better.
88.4%-0.5%vs Muse Spark
Visual reasoning
BabyVisionTests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better.
76.3%+36.4%vs Muse Spark
Community preference
Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better.
1490+2vs Muse Spark
Community preference (code)
Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better.
1540