Skip to main content

DeepSeek V3.1 vs DeepSeek V3.2

SpecDeepSeek V3.1DeepSeek V3.2
Respan Index18.9 (#137)26.6 (#104)
Blended price per 1M$0.425$0.29
Context window128K131K
Input / output per 1M$0.25 / $0.95$0.26 / $0.38
Max output-66K
Inputtexttext
Released2025-08-212025-12-01

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryDeepSeek V3.1DeepSeek V3.2
Coding4.6 DeepSeek V3.18.5 DeepSeek V3.2
Agents10.9 DeepSeek V3.132.0 DeepSeek V3.2
Reasoning25.6 DeepSeek V3.127.9 DeepSeek V3.2
Knowledge & language14.6* DeepSeek V3.120.3 DeepSeek V3.2
Human preference47.8 DeepSeek V3.150.0 DeepSeek V3.2

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

DeepSeek V3.2 leads on 2 of the 2 benchmarks both report. Higher is better. Each score links to where it was published.

FAQ

Is DeepSeek V3.1 better than DeepSeek V3.2?

DeepSeek V3.2 scores 26.6 on the Respan Index (#104), ahead of DeepSeek V3.1 at 18.9 (#137). DeepSeek V3.2 leads on 2 of the 2 benchmarks both report.

Which is cheaper, DeepSeek V3.1 or DeepSeek V3.2?

DeepSeek V3.1 lists at $0.25 input and $0.95 output per 1M tokens; DeepSeek V3.2 at $0.26 and $0.38. DeepSeek V3.2 is 1.5x cheaper per token at list price.

Which has the larger context window?

DeepSeek V3.1 accepts 128K tokens and DeepSeek V3.2 131K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.