← All models
Compare

DeepSeek-V4-Pro-0813 vs Mistral Large 3

DeepSeek-V4-Pro-0813 (DeepSeek) and Mistral Large 3 (Mistral AI) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeDeepSeek-V4-Pro-0813DeepSeek · 1 in the newsMistral Large 3Mistral AI · 4 in the news
Scores
Intelligence (ECI)155
Coding788
Math882
Reasoning & Knowledge707
Agentic & Tools4
Specifications
DeveloperDeepSeekMistral AI
FamilyDeepSeekMistral
ReleasedAug 13, 2026Dec 2, 2025
Parameters1.6T
AvailabilityOpen weights (unrestricted)Open weights (unrestricted)
Context window1M
Price — $/M input$0.58
Price — $/M output$1.74
Inputstext
Outputstext
Benchmarks
AIME 2024/202599%38%
ARC-AGI91%
ARC-AGI-261%
GPQA Diamond92%68%
Humanity's Last Exam41%4%
SciCode51%37%
SimpleQA Verified53%
WebDev Arena15821230
WeirdML66%
LiveCodeBench47%
MMLU-Pro81%
τ²-bench25%

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

Which is better for coding, DeepSeek-V4-Pro-0813 or Mistral Large 3?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro-0813 ranks higher — 78th vs 8th 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.