Muse Spark Open

Leaderboards

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

By task

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

Test results

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

• GPQA

  #35 / 256

  Graduate-level science questions written to be hard to look up.

  89.0%

  Self-reported

• DeepSWE 1.1

  #33 / 50

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

  60.0%

  Self-reported · In the coding score

• Terminal-Bench 2.1

  #25 / 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.

  76.4%

  Self-reported

• MCP Atlas

  #1 / 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.

  89.2%

  Self-reported

• SciCode

  #4 / 30

  SciCode is a research coding benchmark curated by scientists that challenges language models to code solutions for scientific problems. It contains 338 subproblems decomposed from 80 challenging main problems across 16 natural science sub-fields including mathematics, physics, chemistry, biology, and materials science. Problems require knowledge recall, reasoning, and code synthesis skills.

  58.5%

  Self-reported

• OSWorld-Verified

  #10 / 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.

  80.4%

  Self-reported

• SimpleVQA

  #5 / 17

  SimpleVQA is a visual question answering benchmark focused on simple queries.

  0.7%

  Self-reported

• BabyVision

  #6 / 16

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

  80.2%

  Self-reported

• ZEROBench

  #3 / 15

  ZEROBench is a challenging vision benchmark designed to test models on zero-shot visual understanding tasks.

  0.5%

  Self-reported

• GDPval-AA

  #9 / 14

  GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.

  46.7%

  Self-reported

• Artificial Analysis

  #13 / 13

  Artificial Analysis benchmark evaluates AI models across quality, speed, and pricing dimensions, providing a composite assessment of model capabilities for real-world usage.

  39.0%

  Self-reported

• Job Bench

  #2 / 9

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

  61.8%

  Self-reported

• WorldVQA

  #4 / 7

  WorldVQA is a benchmark designed to evaluate atomic vision-centric world knowledge. It assesses models' ability to understand and reason about visual elements representing real-world knowledge.

  49.4%

  Self-reported

• SWE Atlas - Codebase QnA

  #3 / 5

  SWE Atlas - Codebase QnA evaluates a model's ability to answer questions about real codebases, measuring repository-level comprehension and the ability to reason about code structure, behavior, and intent across an entire project.

  58.0%

  Self-reported

• Toolathlon-Verified

  #5 / 5

  Verified Toolathlon evaluation of agent tool-use capability, as reported in the MiMo-V2.6 release.

  72.8%

  Self-reported

• AA-Omniscience Index

  #2 / 4

  AA-Omniscience Index is Artificial Analysis's knowledge-reliability metric. It rewards correct answers, penalizes hallucinations, and does not penalize abstention. Scores range from -100 to 100, where 0 means as many correct as incorrect answers.

  12.5%

  Self-reported

• Humanity's Last Exam (with tools)

  #3 / 4

  Full multimodal Humanity's Last Exam evaluated with tool use enabled, distinct from its text-only subset.

  61.0%

  Self-reported