← All models
Compare

Grok 4 vs Kimi K3

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

grok-4Kimi K3
AttributeGrok 4xAIKimi K3Moonshot · 34 in the news
Scores
Intelligence (ECI)147157
Coding4399
Math2382
Reasoning & Knowledge4778
Agentic & Tools1584
Specifications
DeveloperxAIMoonshot
FamilyGrokKimi
ReleasedJul 9, 2025Jul 16, 2026
Parameters3T2.8T
AvailabilityAPI accessOpen weights (non-commercial)
Context window1M
Price — $/M input$2.80
Price — $/M output$14.00
Inputstext, image, video
Outputstext
Benchmarks
AIME 2024/202584%97%
APEX15%39%
ARC-AGI67%95%
ARC-AGI-216%60%
FrontierMath20%
FrontierMath Tier 42%
GDPval (win/tie rate)24%
GPQA Diamond87%93%
Humanity's Last Exam27%47%
LiveCodeBench82%
METR task horizon1.8 h
MMLU-Pro87%
SciCode46%59%
SimpleBench61%
SimpleQA Verified48%43%
Terminal-Bench27%
WeirdML46%83%
τ²-bench75%
WebDev Arena1682

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.