Muse Spark

Leaderboards

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

• GPQA

  #32 / 256

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

  89.5%

  Self-reported

• SWE-Bench Verified

  #29 / 120

  Fixing real bugs in real GitHub projects, checked by the projects' own tests.

  77.4%

  Self-reported

• Humanity's Last Exam

  #8 / 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

  58.4%

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

• MMMU-Pro

  #14 / 73

  College-level questions that need both an image and text to answer.

  80.4%

  Self-reported · In the vision score

• SWE-Bench Pro

  #50 / 61

  Harder, longer software engineering tasks from real codebases.

  52.4%

  Self-reported · In the coding score

• CharXiv-R

  #14 / 60

  Reading and reasoning about charts from scientific papers.

  86.4%

  Self-reported

• Terminal-Bench 2.0

  #24 / 54

  Getting real work done in a command-line terminal.

  59.0%

  Self-reported

• Tau2 Telecom

  #16 / 36

  τ²-Bench telecom domain evaluates conversational agents in a dual-control environment modeled as a Dec-POMDP, where both agent and user use tools in shared telecommunications troubleshooting scenarios that test coordination and communication capabilities.

  91.5%

  Self-reported

• ERQA

  #12 / 29

  Embodied Reasoning Question Answering benchmark consisting of 400 multiple-choice visual questions across spatial reasoning, trajectory reasoning, action reasoning, state estimation, and multi-view reasoning for evaluating AI capabilities in physical world interactions

  64.7%

  Self-reported

• ScreenSpot Pro

  #6 / 27

  ScreenSpot-Pro is a novel GUI grounding benchmark designed to rigorously evaluate the grounding capabilities of multimodal large language models (MLLMs) in professional high-resolution computing environments. The benchmark comprises 1,581 instructions across 23 applications spanning 5 industries and 3 operating systems, featuring authentic high-resolution images from professional domains with expert annotations. Unlike previous benchmarks that focus on cropped screenshots in consumer applications, ScreenSpot-Pro addresses the complexity and diversity of real-world professional software scenarios, revealing significant performance gaps in current MLLM GUI perception capabilities.

  84.1%

  Self-reported

• HealthBench Hard

  #1 / 24

  A challenging variation of HealthBench that evaluates large language models' performance and safety in healthcare through 5,000 multi-turn conversations with particularly rigorous evaluation criteria validated by 262 physicians from 60 countries

  42.8%

  Self-reported

• ARC-AGI v2

  #10 / 19

  ARC-AGI-2 is an upgraded benchmark for measuring abstract reasoning and problem-solving abilities in AI systems through visual grid transformation tasks. It evaluates fluid intelligence via input-output grid pairs (1x1 to 30x30) using colored cells (0-9), requiring models to identify underlying transformation rules from demonstration examples and apply them to test cases. Designed to be easy for humans but challenging for AI, focusing on core cognitive abilities like spatial reasoning, pattern recognition, and compositional generalization.

  42.5%

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

• SimpleVQA

  #6 / 17

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

  0.7%

  Self-reported

• ZEROBench

  #7 / 15

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

  0.3%

  Self-reported

• MedXpertQA

  #1 / 12

  A comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning, featuring 4,460 questions spanning 17 specialties and 11 body systems. Includes both text-only and multimodal subsets with expert-level exam questions incorporating diverse medical images and rich clinical information.

  78.4%

  Self-reported

• DeepSearchQA

  #9 / 10

  DeepSearchQA is a benchmark for evaluating deep search and question-answering capabilities, testing models' ability to perform multi-hop reasoning and information retrieval across complex knowledge domains.

  74.8%

  Self-reported

• FrontierScience Research

  #1 / 5

  FrontierScience Research is a benchmark evaluating AI models on cutting-edge scientific research questions requiring deep domain expertise, multi-step reasoning, and synthesis of complex scientific concepts across disciplines.

  38.3%

  Self-reported

• LiveCodeBench Pro

  #5 / 5

  LiveCodeBench Pro is an advanced evaluation benchmark for large language models for code that uses Elo ratings to rank models based on their performance on coding tasks. It evaluates models on real-world coding problems from programming contests (LeetCode, AtCoder, CodeForces) and provides a relative ranking system where higher Elo scores indicate superior performance.

  0.0%

  Self-reported

• IPhO 2025

  #1 / 2

  International Physics Olympiad 2025 (theory) comprises all 3 theory problems from the official 2025 IPhO competition. Results are based on blinded human evaluation with guidelines based on the official competition scoring, validated by domain experts.

  82.6%

  Unverified