← All models
Compare

DeepSeek-V4-Pro vs Gemini 3.1 Pro

DeepSeek-V4-Pro (DeepSeek) and Gemini 3.1 Pro (Google DeepMind) compared on benchmarks, pricing, context window, and use-case rankings.

DeepSeek-V4-ProDeepSeek · 3 in the newsGemini 3.1 ProGoogle DeepMind · 3 in the news
Scores
Intelligence (ECI)150155
Coding7668
Math9177
Reasoning & Knowledge6896
Agentic & Tools9288
Specifications
DeveloperDeepSeekGoogle DeepMind
FamilyDeepSeekGemini
ReleasedApr 24, 2026Feb 19, 2026
Parameters1.6T
AvailabilityOpen weights (unrestricted)API access
Context window1M
Price — $/M input$0.43
Price — $/M output$0.87
Inputstext
Outputstext
Benchmarks
AIME 2024/202597%96%
GPQA Diamond90%94%
Humanity's Last Exam36%46%
SciCode50%
SimpleBench61%80%
SimpleQA Verified57%77%
SWE-bench Verified78%76%
WebDev Arena14641461
WeirdML49%72%
τ²-bench96%
APEX34%
ARC-AGI98%
ARC-AGI-277%
FrontierMath37%
FrontierMath Tier 417%
GSO (code optimization)23%
METR task horizon6.4 h
Terminal-Bench80%

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 better than Gemini 3.1 Pro?

On Epoch AI's Capabilities Index, Gemini 3.1 Pro scores higher (155) than DeepSeek-V4-Pro (150). 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 or Gemini 3.1 Pro?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro ranks higher — 76th vs 68th 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.