Skip to main content

Mistral Medium 3.5 vs o3

SpecMistral Medium 3.5o3
Respan Index26.2 (#105)25.8 (#107)
Blended price per 1M$3$3.5
Context window256K200K
Input / output per 1M$1.5 / $7.5$2 / $8
Max output-100K
Inputtext, visiontext, vision
Released2026-04-282025-04-16

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 Medium 3.5o3
Coding6.8 Mistral Medium 3.57.8 o3
Agents42.6 Mistral Medium 3.58.3 o3
Reasoning20.4 Mistral Medium 3.538.1 o3
Knowledge & language17.0* Mistral Medium 3.549.3 o3
Human preference47.3 Mistral Medium 3.549.1 o3

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

Benchmarks both report

o3 leads on 4 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkMistral Medium 3.5o3
LMArena Elo14261432
LMArena Vision (LMArena)11991216
SAGE (Vals AI)37.6%41.8%
WeirdML (Håvard Tveit Ihle)43.7%52.4%
SWE-bench Verified77.6%69.1%

FAQ

Is Mistral Medium 3.5 better than o3?

Mistral Medium 3.5 scores 26.2 on the Respan Index (#105), ahead of o3 at 25.8 (#107). o3 leads on 4 of the 5 benchmarks both report.

Which is cheaper, Mistral Medium 3.5 or o3?

Mistral Medium 3.5 lists at $1.5 input and $7.5 output per 1M tokens; o3 at $2 and $8. Mistral Medium 3.5 is 1.2x cheaper per token at list price.

Which has the larger context window?

Mistral Medium 3.5 accepts 256K tokens and o3 200K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.