Skip to main content

Mistral Large 4 vs Mistral Medium 3.5

SpecMistral Large 4Mistral Medium 3.5
Respan Index44.1 (#59)26.2 (#105)
Blended price per 1M$1.05$3
Context window1M256K
Input / output per 1M$0.7 / $2.1$1.5 / $7.5
Max output--
Inputtext, visiontext, vision
Released2026-10-062026-04-28

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.

CategoryMistral Large 4Mistral Medium 3.5
Coding37.3 Mistral Large 46.8 Mistral Medium 3.5
Agents56.7 Mistral Large 442.6 Mistral Medium 3.5
Reasoning42.1 Mistral Large 420.4 Mistral Medium 3.5
Knowledge & language18.2 Mistral Large 417.0* Mistral Medium 3.5
Human preference55.3 Mistral Large 447.3 Mistral Medium 3.5

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

Benchmarks both report

Mistral Large 4 leads on 3 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkMistral Large 4Mistral Medium 3.5
LMArena Agent (LMArena)-0.0715-0.1446
LMArena Elo14221426
LMArena WebDev (LMArena)15681263
LMArena Vision (LMArena)12311199

FAQ

Is Mistral Large 4 better than Mistral Medium 3.5?

Mistral Large 4 scores 44.1 on the Respan Index (#59), ahead of Mistral Medium 3.5 at 26.2 (#105). Mistral Large 4 leads on 3 of the 4 benchmarks both report.

Which is cheaper, Mistral Large 4 or Mistral Medium 3.5?

Mistral Large 4 lists at $0.7 input and $2.1 output per 1M tokens; Mistral Medium 3.5 at $1.5 and $7.5. Mistral Large 4 is 2.9x cheaper per token at list price.

Which has the larger context window?

Mistral Large 4 accepts 1M tokens and Mistral Medium 3.5 256K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.