← All models
Compare

DeepSeek-V4-Pro-0813 vs Gemini 3 Flash

DeepSeek-V4-Pro-0813 (DeepSeek) and Gemini 3 Flash (Google DeepMind) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeDeepSeek-V4-Pro-0813DeepSeek · 1 in the newsGemini 3 FlashGoogle DeepMind · 2 in the news
Scores
Intelligence (ECI)155152
Coding7837
Math8853
Reasoning & Knowledge7056
Agentic & Tools58
Specifications
DeveloperDeepSeekGoogle DeepMind
FamilyDeepSeekGemini
ReleasedAug 13, 2026Dec 17, 2025
Parameters1.6T
AvailabilityOpen weights (unrestricted)API access
Context window1M
Price — $/M input$0.58
Price — $/M output$1.74
Inputstext
Outputstext
Benchmarks
AIME 2024/202599%96%
ARC-AGI91%85%
ARC-AGI-261%34%
GPQA Diamond92%89%
Humanity's Last Exam41%
SciCode51%
SimpleQA Verified53%67%
WebDev Arena15821383
WeirdML66%62%
APEX24%
FrontierMath36%
FrontierMath Tier 44%
GSO (code optimization)10%
SimpleBench61%
SWE-bench Verified75%
Terminal-Bench64%

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 Gemini 3 Flash?

On Epoch AI's Capabilities Index, DeepSeek-V4-Pro-0813 scores higher (155) than Gemini 3 Flash (152). 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 Gemini 3 Flash?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro-0813 ranks higher — 78th vs 37th 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.