Skip to main content

DeepSeek V3.2 vs Mistral Medium 3.5

SpecDeepSeek V3.2Mistral Medium 3.5
Respan Index26.6 (#104)26.3 (#106)
Blended price per 1M$0.29$3
Context window131K256K
Input / output per 1M$0.26 / $0.38$1.5 / $7.5
Max output66K-
Inputtexttext, vision
Released2025-12-012026-04-28

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 V3.2Mistral Medium 3.5
Coding8.5 DeepSeek V3.26.7 Mistral Medium 3.5
Agents32.0 DeepSeek V3.242.9 Mistral Medium 3.5
Reasoning27.9 DeepSeek V3.220.4 Mistral Medium 3.5
Knowledge & language20.3 DeepSeek V3.217.1* Mistral Medium 3.5
Human preference50.0 DeepSeek V3.247.5 Mistral Medium 3.5

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

Benchmarks both report

Mistral Medium 3.5 leads on 2 of the 3 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkDeepSeek V3.2Mistral Medium 3.5
LMArena Elo14251426
LMArena WebDev (LMArena)13631263
SWE-bench Verified73.1%77.6%

FAQ

Is DeepSeek V3.2 better than Mistral Medium 3.5?

DeepSeek V3.2 scores 26.6 on the Respan Index (#104), ahead of Mistral Medium 3.5 at 26.3 (#106). Mistral Medium 3.5 leads on 2 of the 3 benchmarks both report.

Which is cheaper, DeepSeek V3.2 or Mistral Medium 3.5?

DeepSeek V3.2 lists at $0.26 input and $0.38 output per 1M tokens; Mistral Medium 3.5 at $1.5 and $7.5. DeepSeek V3.2 is 10x cheaper per token at list price.

Which has the larger context window?

DeepSeek V3.2 accepts 131K tokens and Mistral Medium 3.5 256K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.