← All models
Compare

DeepSeek-V4-Pro-0813 vs Grok 4.3 Beta

DeepSeek-V4-Pro-0813 (DeepSeek) and Grok 4.3 Beta (xAI) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeDeepSeek-V4-Pro-0813DeepSeek · 1 in the newsGrok 4.3 BetaxAI
Scores
Intelligence (ECI)155149
Coding7621
Math8859
Reasoning & Knowledge6941
Agentic & Tools67
Specifications
DeveloperDeepSeekxAI
FamilyDeepSeekGrok
ReleasedAug 13, 2026Apr 17, 2026
Parameters1.6T
AvailabilityOpen weights (unrestricted)Hosted access (no API)
Context window1M
Price — $/M input$0.58
Price — $/M output$1.74
Inputstext
Outputstext
Benchmarks
AIME 2024/202599%93%
APEX47%
ARC-AGI91%
ARC-AGI-261%
GPQA Diamond92%89%
Humanity's Last Exam41%
SciCode51%
SimpleQA Verified53%33%
WebDev Arena15811357
WeirdML66%50%

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.

Frequently asked questions

Is DeepSeek-V4-Pro-0813 better than Grok 4.3 Beta?

On Epoch AI's Capabilities Index, DeepSeek-V4-Pro-0813 scores higher (155) than Grok 4.3 Beta (149). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.

Which is better for coding, DeepSeek-V4-Pro-0813 or Grok 4.3 Beta?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro-0813 ranks higher — 76th vs 21th percentile among the models tracked on Model Beat.

Want a different match-up? Open the compare tool to add or swap models.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.