← All models
Compare

Muse Spark vs Qwen3-Omni-30B-A3B

Add, remove, or swap models to compare them side by side.

Muse SparkQwen3-Omni-30B-A3B
AttributeMuse SparkMeta AI · 1 in the newsQwen3-Omni-30B-A3BAlibaba
Scores
Intelligence (ECI)153
Coding7613
Math6413
Reasoning & Knowledge8210
Agentic & Tools631
Specifications
DeveloperMeta AIAlibaba
FamilyQwen
ReleasedApr 8, 2026Sep 22, 2025
Parameters35.3B
AvailabilityAPI accessOpen weights (unrestricted)
Context window
Price — $/M input
Price — $/M output
Inputs
Outputs
Benchmarks
AIME 2024/202589%74%
FrontierMath39%
FrontierMath Tier 415%
GPQA Diamond90%73%
Humanity's Last Exam41%7%
SciCode52%31%
SimpleQA Verified66%
WebDev Arena1513
τ²-bench92%21%
LiveCodeBench68%
MMLU-Pro79%

Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.