Ministral 3 3B vs Ministral 3 8B

Which is better for the money: Ministral 3 3B by Mistral or Ministral 3 8B by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.

Trade-off

MistralMinistral 3 3BOn the open-weights frontier

Intelligence: 4.80
Total cost: $12.2

MistralMinistral 3 8BOff the frontier

Intelligence: 5.50
Total cost: $27.5

Verdict

Depends on your budget

Ministral 3 8B scores 0.7 points higher (5.5 vs 4.8) but costs 2.2× as much to run the benchmark ($27.5 vs $12.2; both budget class). Pick Ministral 3 8B when the extra intelligence is worth the premium, otherwise Ministral 3 3B.

Metric	Ministral 3 3B	Ministral 3 8B	Difference
Intelligence (higher is better)	4.8	5.5	+14.6% Ministral 3 8B is 14.6% more intelligent
Total AA cost (lower is better)	$12.23	$27.47	+124.6% Ministral 3 8B is 2.2× more expensive
End-to-end time (lower is better)	3.32s	6.23s	+87.7% Ministral 3 8B is 87.7% slower
Price per 1M tokens (in / out)	$0.10 / $0.10	$0.15 / $0.15
Input modalities	Text, Image	Text, Image

Ministral 3 8B vs Ministral 3 3B: 14.6% more intelligence, 124.6% more cost to run the AA benchmark, and 87.7% slower end-to-end.

Open this matchup in the interactive picker Ministral 3 3B: what beats it Ministral 3 8B: what beats it

Today's Pareto frontier

Against the frontier

Ministral 3 3B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Ministral 3 8B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.

Ministral 3 3BMinistral 3 8BToday'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/ministral-3-3b/ministral-3-8b · Markdown: /api/v1/compare/ministral-3-3b/ministral-3-8b?format=md · llms.txt · agent skill