Granite 4.2 30B vs Granite 4.2 3B

Which is better for the money: Granite 4.2 30B by IBM or Granite 4.2 3B by IBM? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.

Trade-off

IBMGranite 4.2 30BOff the frontier

Intelligence: 12.70
Total cost: $111

IBMGranite 4.2 3BOn the open-weights frontier

Intelligence: 9.10
Total cost: $14.9

Verdict

Depends on your budget

Granite 4.2 30B scores 3.6 points higher (12.7 vs 9.1) but costs 7.4× as much to run the benchmark ($111 vs $14.9; mid-range vs budget cost classes). They are not alternatives at one budget: pick Granite 4.2 30B when you need intelligence above 9.1, and Granite 4.2 3B when 9.1 is enough.

Metric	Granite 4.2 30B	Granite 4.2 3B	Difference
Intelligence (higher is better)	12.7	9.1	−28.3% Granite 4.2 3B is 28.3% less intelligent
Total AA cost (lower is better)	$110.83	$14.91	−86.5% Granite 4.2 3B is 86.5% cheaper
End-to-end time (lower is better)	54.96s	49.98s	−9.1% Granite 4.2 3B is 9.1% faster
Price per 1M tokens (in / out)	$0.16 / $0.65	$0.03 / $0.12
Input modalities	Text	Text

Granite 4.2 3B vs Granite 4.2 30B: 28.3% less intelligence, 86.5% less cost to run the AA benchmark, and 9.1% faster end-to-end.

Open this matchup in the interactive picker Granite 4.2 30B: what beats it Granite 4.2 3B: what beats it

Today's Pareto frontier

Against the frontier

Granite 4.2 30B is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
Granite 4.2 3B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.

Granite 4.2 30BGranite 4.2 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-4-2-30b/granite-4-2-3b · Markdown: /api/v1/compare/granite-4-2-30b/granite-4-2-3b?format=md · llms.txt · agent skill