Granite 4.2 3B vs Ministral 3 14B

Which is better for the money: Granite 4.2 3B by IBM or Ministral 3 14B by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.

Clear winner

IBMGranite 4.2 3BOn the open-weights frontier

Intelligence: 9.10
Total cost: $14.9

MistralMinistral 3 14BOff the frontier

Intelligence: 6.00
Total cost: $37.6

Verdict

Pick Granite 4.2 3B

Ministral 3 14B vs Granite 4.2 3B: 34.1% less intelligence, 151.9% more cost to run the AA benchmark, and 87.2% faster end-to-end.

Metric	Granite 4.2 3B	Ministral 3 14B	Difference
Intelligence (higher is better)	9.1	6.0	−34.1% Ministral 3 14B is 34.1% less intelligent
Total AA cost (lower is better)	$14.91	$37.56	+151.9% Ministral 3 14B is 2.5× more expensive
End-to-end time (lower is better)	62.62s	8.02s	−87.2% Ministral 3 14B is 87.2% faster
Price per 1M tokens (in / out)	$0.03 / $0.12	$0.20 / $0.20
Input modalities	Text	Text, Image

Open this matchup in the interactive picker Granite 4.2 3B: what beats it Ministral 3 14B: 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 14B is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.

Granite 4.2 3BMinistral 3 14BToday'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-3-14b · Markdown: /api/v1/compare/granite-4-2-3b/ministral-3-14b?format=md · llms.txt · agent skill