← All models
Compare

DeepSeek-V3.1 vs Grok 4.5

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

DeepSeek-V3.1Grok 4.5
AttributeDeepSeek-V3.1DeepSeekGrok 4.5xAI · 2 in the news
Scores
Intelligence (ECI)139154
Coding1489
Math384
Reasoning & Knowledge1668
Agentic & Tools1074
Specifications
DeveloperDeepSeekxAI
FamilyDeepSeekGrok
ReleasedAug 21, 2025Jul 8, 2026
Parameters
AvailabilityOpen weights (unrestricted)API access
Context window500K
Price — $/M input$2.00
Price — $/M output$6.00
Inputstext, image, file
Outputstext
Benchmarks
AIME 2024/202550%98%
GPQA Diamond74%93%
Humanity's Last Exam6%40%
LiveCodeBench58%
MMLU-Pro83%
SciCode37%54%
SimpleBench40%70%
WeirdML38%46%
τ²-bench35%
APEX34%
ARC-AGI87%
ARC-AGI-253%
SimpleQA Verified54%
WebDev Arena1551

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.