Granite 4.2 3B vs Ministral 3 3B

Which is better for the money: Granite 4.2 3B by IBM or Ministral 3 3B by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.

Trade-off

IBMGranite 4.2 3BOn the open-weights frontier

Intelligence: 9.10
Total cost: $14.9

MistralMinistral 3 3BOn the open-weights frontier

Intelligence: 4.80
Total cost: $12.2

Verdict

Depends on your budget

Granite 4.2 3B scores 4.3 points higher (9.1 vs 4.8) but costs 1.2× as much to run the benchmark ($14.9 vs $12.2; both budget class). Pick Granite 4.2 3B when the extra intelligence is worth the premium, otherwise Ministral 3 3B.

Metric	Granite 4.2 3B	Ministral 3 3B	Difference
Intelligence (higher is better)	9.1	4.8	−47.3% Ministral 3 3B is 47.3% less intelligent
Total AA cost (lower is better)	$14.91	$12.23	−18.0% Ministral 3 3B is 18.0% cheaper
End-to-end time (lower is better)	62.62s	3.07s	−95.1% Ministral 3 3B is 95.1% faster
Price per 1M tokens (in / out)	$0.03 / $0.12	$0.10 / $0.10
Input modalities	Text	Text, Image

Ministral 3 3B vs Granite 4.2 3B: 47.3% less intelligence, 18.0% less cost to run the AA benchmark, and 95.1% faster end-to-end.

Open this matchup in the interactive picker Granite 4.2 3B: what beats it Ministral 3 3B: what beats it

Today's Pareto frontier

Against the frontier

Granite 4.2 3B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Ministral 3 3B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.

Granite 4.2 3BMinistral 3 3BToday'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/granite-4-2-3b/ministral-3-3b · Markdown: /api/v1/compare/granite-4-2-3b/ministral-3-3b?format=md · llms.txt · agent skill