Mistral Medium 3.5 vs Mistral Small Creative

$0.50 / task
Wins 0 of 5 benchmarks
Wins 0 of 5 benchmarks
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
Mistral Medium 3.513.8
Mistral Small Creative—
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Mistral Medium 3.50
Mistral Small Creative—
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation
Mistral Medium 3.56.3
Mistral Small Creative—
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
Mistral Medium 3.51,400
Mistral Small Creative—
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos
Mistral Medium 3.564.9
Mistral Small Creative—

Specs

SpecMistral Medium 3.5Mistral Small Creative
Input, per 1M$1.50—
Output, per 1M$7.50—
Cost per task?$0.50—
Speed, tok/s155—
Context262K—
WeightsOpenNot verified
ReleasedApr 2026—
Memory (4-bit)77 GB—
Licencecustom licence—
Commercial useRestricted—
See images✓?
Read PDFs✓?
Hear audio—?
Watch video—?
Call tools✓?
Force a tool callPartial?
Return strict JSON✓?
Search the web??
Run code??
Use a computer??

What breaks when you switch

Mistral Medium 3.5 → Mistral Small Creative
Context: not verified
Mistral Small Creative → Mistral Medium 3.5
Nothing known.