← All models
Compare

GPT-5.5 vs Muse Spark

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

GPT-5.5Muse Spark
GPT-5.5OpenAI · 17 in the newsMuse SparkMeta AI
Scores
Intelligence (ECI)159155
Coding9184
Math9769
Reasoning & Knowledge9286
Agentic & Tools8762
Specifications
DeveloperOpenAIMeta AI
FamilyGPT
ReleasedApr 23, 2026Apr 8, 2026
Parameters
AvailabilityAPI accessAPI access
Context window1.1M
Price — $/M input$5.00
Price — $/M output$30.00
Inputsfile, image, text
Outputstext
Benchmarks
AIME 2024/2025100%89%
APEX38%
ARC-AGI95%
ARC-AGI-285%
FrontierMath52%39%
FrontierMath Tier 435%15%
GPQA Diamond94%90%
GSO (code optimization)40%
Humanity's Last Exam44%41%
SciCode56%52%
SimpleBench69%
SimpleQA Verified63%66%
SWE-bench Verified81%
Terminal-Bench85%
WebDev Arena15051513
WeirdML85%
τ²-bench94%92%

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.