← All models
Compare

GPT-5.3 Codex vs Grok 4.6

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

GPT-5.3 CodexGrok 4.6
AttributeGPT-5.3 CodexOpenAI · 4 in the newsGrok 4.6xAI · 3 in the news
Scores
Intelligence (ECI)156156
Coding5690
Math91
Reasoning & Knowledge8473
Agentic & Tools5795
Specifications
DeveloperOpenAIxAI
FamilyGPTGrok
ReleasedFeb 5, 2026Aug 12, 2026
Parameters
AvailabilityAPI accessAPI access
Context window400K500K
Price — $/M input$1.75$2.00
Price — $/M output$14.00$6.00
Inputstext, image, filetext, image, file
Outputstexttext
Benchmarks
APEX32%65%
GPQA Diamond92%94%
Humanity's Last Exam43%43%
METR task horizon5.8 h
SciCode53%56%
SWE-bench Verified75%
Terminal-Bench78%
WebDev Arena13701618
WeirdML79%67%
τ²-bench86%
AIME 2024/202599%
ARC-AGI88%
ARC-AGI-267%
SimpleBench76%
SimpleQA Verified49%

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.