← All models
Compare

DeepSeek-V3.2 vs Grok 4

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

DeepSeek-V3.2Grok 4
DeepSeek-V3.2DeepSeek · 1 in the newsGrok 4xAI
Scores
Intelligence (ECI)146147
Coding2715
Math3622
Reasoning & Knowledge2648
Agentic & Tools2916
Specifications
DeveloperDeepSeekxAI
FamilyDeepSeekGrok
ReleasedDec 1, 2025Jul 9, 2025
Parameters3T
AvailabilityOpen weights (unrestricted)API access
Context window131K
Price — $/M input$0.23
Price — $/M output$0.34
Inputstext
Outputstext
Benchmarks
AIME 2024/202588%84%
APEX7%15%
ARC-AGI57%67%
ARC-AGI-24%16%
FrontierMath22%20%
FrontierMath Tier 42%2%
GPQA Diamond83%87%
SimpleBench53%61%
SimpleQA Verified28%48%
Terminal-Bench40%27%
WebDev Arena1286
WeirdML47%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.