GPT-6 Luna (Max) vs Ministral 3 8B

Which is better for the money: GPT-6 Luna (Max) by OpenAI or Ministral 3 8B by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.

Trade-off

OpenAIGPT-6 Luna (Max)On the frontier

Intelligence: 38.10
Total cost: $122

MistralMinistral 3 8BOff the frontier

Intelligence: 5.50
Total cost: $27.5

Verdict

Depends on your budget

GPT-6 Luna (Max) scores 32.6 points higher (38.1 vs 5.5) but costs 4.4× as much to run the benchmark ($122 vs $27.5; mid-range vs budget cost classes). They are not alternatives at one budget: pick GPT-6 Luna (Max) when you need intelligence above 5.5, and Ministral 3 8B when 5.5 is enough.

Metric	GPT-6 Luna (Max)	Ministral 3 8B	Difference
Intelligence (higher is better)	38.1	5.5	−85.6% Ministral 3 8B is 85.6% less intelligent
Total AA cost (lower is better)	$122.05	$27.47	−77.5% Ministral 3 8B is 77.5% cheaper
End-to-end time (lower is better)	90.27s	5.26s	−94.2% Ministral 3 8B is 94.2% faster
Price per 1M tokens (in / out)	$0.10 / $0.50	$0.15 / $0.15
Input modalities	Text, Image	Text, Image

Ministral 3 8B vs GPT-6 Luna (Max): 85.6% less intelligence, 77.5% less cost to run the AA benchmark, and 94.2% faster end-to-end.

Open this matchup in the interactive picker GPT-6 Luna (Max): what beats it Ministral 3 8B: what beats it

Today's Pareto frontier

Against the frontier

GPT-6 Luna (Max) is on today's frontier: nothing is both smarter and cheaper.
Ministral 3 8B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.

GPT-6 Luna (Max)Ministral 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/gpt-6-luna/ministral-3-8b · Markdown: /api/v1/compare/gpt-6-luna/ministral-3-8b?format=md · llms.txt · agent skill