Skip to content

Meta Proprietary Released Jul 9, 2026 Updated

Muse Spark 1.1

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #20 / 416

    568 / 1,000

    ToolsGuide Score· votes only

  • Vision #17 / 167

    574 / 1,000

    ToolsGuide Score· votes 532, tests 616

  • Coding #50 / 147

    392 / 1,000

    ToolsGuide Score· votes 394, tests 391

  • Agents #30 / 53

    457 / 1,000

    ToolsGuide Score· votes 419, tests 475

  • Price per 1M tokens

    In $1.25· Out $4.25

    $1.25

    Input · median text model $0.43

Summary

Muse Spark 1.1 is Meta's model, released Jul 9, 2026. It's ranked in 4 categories and does best at text: #20 of 416, with a ToolsGuide Score of 568 against a median of 235.

It also ranks #17 of 167 for vision (574), #50 of 147 for coding (392), #30 of 53 for agents (457).

Its text score uses votes only, because it has published fewer than two of the tests used for that category.

It costs $1.25 per million input tokens and $4.25 per million output tokens, about 2.9× the median text model ($0.43).

It has published results on 11 tests.

Specifications

Creator
Meta
Licence
Proprietary
Released
Jul 9, 2026
Context window
1M tokens
Input price
$1.25 / 1M
Output price
$4.25 / 1M
Tests reported
11
Settings ranked
Muse Spark 1.1

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Vision score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where Muse Spark 1.1 sits among the top 20 in each category.

Text

#20 of 416 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

Vision

#17 of 167 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full vision leaderboard →

Coding

#50 of 147 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full coding leaderboard →

Agents

#30 of 53 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full agents leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Score against price

Text · the 10 priced models ranked closest · up and to the left is better value

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

Muse Spark 1.1 · hover a bar for its rank

Vision

Muse Spark 1.1 · hover a bar for its rank

Coding

Muse Spark 1.1 · hover a bar for its rank

Test results

Every test Muse Spark 1.1 has a published result on, out of 100%, with its rank among the models that took it.

  • Humanity's Last Exam

    #6 / 108

    Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

    62.1%

    Self-reported · In the text score· In the vision score

  • SWE-Bench Pro

    #19 / 61

    Harder, longer software engineering tasks from real codebases.

    61.5%

    Self-reported · In the coding score

  • CharXiv-R

    #11 / 60

    Reading and reasoning about charts from scientific papers.

    88.4%

    Self-reported

  • DeepSWE 1.1

    #41 / 50

    DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

    53.0%

    Self-reported · In the coding score

  • Terminal-Bench 2.1

    #23 / 46

    Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal. It evaluates how well models handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, data science workflows, and security tasks.

    80.0%

    Self-reported

  • Toolathlon

    #2 / 42

    Tool Decathlon is a comprehensive benchmark for evaluating AI agents' ability to use multiple tools across diverse task categories. It measures proficiency in tool selection, sequencing, and execution across ten different tool-use scenarios.

    75.6%

    Self-reported · In the agents score

  • MCP Atlas

    #2 / 38

    MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

    88.1%

    Self-reported

  • Finance Agent v2

    #3 / 28

    Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.

    57.2%

    Self-reported

  • OSWorld-Verified

    #8 / 28

    OSWorld-Verified is a verified subset of OSWorld, a scalable real computer environment for multimodal agents supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS.

    80.8%

    Self-reported

  • BabyVision

    #7 / 16

    A benchmark for early-stage visual reasoning and perception on child-like vision tasks.

    76.3%

    Self-reported

  • Job Bench

    #6 / 9

    Job Bench evaluates AI agents on realistic professional tasks that require multi-step planning, research, and production of work artifacts.

    54.7%

    Self-reported