← All models
Compare

DeepSeek-V3.2 vs Gemini 3.1 Pro

DeepSeek-V3.2 (DeepSeek) and Gemini 3.1 Pro (Google DeepMind) compared on benchmarks, pricing, context window, and use-case rankings.

DeepSeek-V3.2DeepSeek · 1 in the newsGemini 3.1 ProGoogle DeepMind · 2 in the news
Scores
Intelligence (ECI)146156
Coding2771
Math3676
Reasoning & Knowledge2696
Agentic & Tools2988
Specifications
DeveloperDeepSeekGoogle DeepMind
FamilyDeepSeekGemini
ReleasedDec 1, 2025Feb 19, 2026
Parameters
AvailabilityOpen weights (unrestricted)API access
Context window131K
Price — $/M input$0.23
Price — $/M output$0.34
Inputstext
Outputstext
Benchmarks
AIME 2024/202588%96%
APEX7%34%
ARC-AGI57%98%
ARC-AGI-24%77%
FrontierMath22%37%
FrontierMath Tier 42%17%
GPQA Diamond83%94%
SimpleBench53%80%
SimpleQA Verified28%77%
Terminal-Bench40%80%
WebDev Arena12861461
WeirdML47%72%
GSO (code optimization)23%
Humanity's Last Exam46%
METR task horizon6.4 h
SWE-bench Verified76%

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-V3.2 better than Gemini 3.1 Pro?

On Epoch AI's Capabilities Index, Gemini 3.1 Pro scores higher (156) than DeepSeek-V3.2 (146). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.

Which is better for coding, DeepSeek-V3.2 or Gemini 3.1 Pro?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Gemini 3.1 Pro ranks higher — 71th vs 27th 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.