← All models
Compare

GPT-5.5 vs Grok 4

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

GPT-5.5Grok 4
GPT-5.5OpenAI · 14 in the newsGrok 4xAI
Scores
Intelligence (ECI)159147
Coding8915
Math9722
Reasoning & Knowledge9148
Agentic & Tools9516
Specifications
DeveloperOpenAIxAI
FamilyGPTGrok
ReleasedApr 23, 2026Jul 9, 2025
Parameters3T
AvailabilityAPI accessAPI access
Context window1.1M
Price — $/M input$5.00
Price — $/M output$30.00
Inputsfile, image, text
Outputstext
Benchmarks
AIME 2024/2025100%84%
APEX38%15%
ARC-AGI95%67%
ARC-AGI-285%16%
FrontierMath52%20%
FrontierMath Tier 435%2%
GPQA Diamond94%87%
GSO (code optimization)40%
SimpleBench69%61%
SimpleQA Verified63%48%
SWE-bench Verified81%
Terminal-Bench85%27%
WebDev Arena1505
WeirdML85%46%
GDPval (win/tie rate)24%
METR task horizon1.8 h

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.