Mistral Small 3.2 vs Mistral Small 4 (Reasoning)

Which is better for the money: Mistral Small 3.2 by Mistral or Mistral Small 4 (Reasoning) by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.

Clear winner

MistralMistral Small 3.2Off the frontier

Intelligence: 7.00
Total cost: $122

MistralMistral Small 4 (Reasoning)On the open-weights frontier

Intelligence: 11.30
Total cost: $42.5

Verdict

Pick Mistral Small 4 (Reasoning)

Mistral Small 4 (Reasoning) vs Mistral Small 3.2: 61.4% more intelligence, 65.1% less cost to run the AA benchmark, and 16.0% slower end-to-end.

Metric	Mistral Small 3.2	Mistral Small 4 (Reasoning)	Difference
Intelligence (higher is better)	7.0	11.3	+61.4% Mistral Small 4 (Reas… is 61.4% more intelligent
Total AA cost (lower is better)	$121.78	$42.50	−65.1% Mistral Small 4 (Reas… is 65.1% cheaper
End-to-end time (lower is better)	12.50s	14.50s	+16.0% Mistral Small 4 (Reas… is 16.0% slower
Price per 1M tokens (in / out)	$0.07 / $0.20	$0.15 / $0.60
Input modalities	Text, Image	Text, Image

Open this matchup in the interactive picker Mistral Small 3.2: what beats it Mistral Small 4 (Reasoning): what beats it

Today's Pareto frontier

Against the frontier

Mistral Small 3.2 is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.

Mistral Small 3.2Mistral Small 4 (Reasoning)Today's Pareto frontierOpen-weights frontierEvery other model

Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/mistral-small-3-2/mistral-small-4 · Markdown: /api/v1/compare/mistral-small-3-2/mistral-small-4?format=md · llms.txt · agent skill