← All models
Compare

DeepSeek-V4-Pro vs Muse Spark

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

DeepSeek-V4-ProMuse Spark
DeepSeek-V4-ProDeepSeek · 3 in the newsMuse SparkMeta AI
Scores
Intelligence (ECI)150155
Coding7684
Math9169
Reasoning & Knowledge6886
Agentic & Tools9262
Specifications
DeveloperDeepSeekMeta AI
FamilyDeepSeek
ReleasedApr 24, 2026Apr 8, 2026
Parameters1.6T
AvailabilityOpen weights (unrestricted)API access
Context window1M
Price — $/M input$0.43
Price — $/M output$0.87
Inputstext
Outputstext
Benchmarks
AIME 2024/202597%89%
GPQA Diamond90%90%
Humanity's Last Exam36%41%
SciCode50%52%
SimpleBench61%
SimpleQA Verified57%66%
SWE-bench Verified78%
WebDev Arena14641513
WeirdML49%
τ²-bench96%92%
FrontierMath39%
FrontierMath Tier 415%

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.