GPT-6 Luna (Low) vs Mistral Small 4 (Reasoning)

Which is better for the money: GPT-6 Luna (Low) by OpenAI or Mistral Small 4 (Reasoning) by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.

Clear winner

OpenAIGPT-6 Luna (Low)On the frontier

Intelligence: 21.50
Total cost: $10.6

MistralMistral Small 4 (Reasoning)On the open-weights frontier

Intelligence: 11.30
Total cost: $42.5

Verdict

Pick GPT-6 Luna (Low)

Mistral Small 4 (Reasoning) vs GPT-6 Luna (Low): 47.4% less intelligence, 299.8% more cost to run the AA benchmark, and 119.9% slower end-to-end.

Metric	GPT-6 Luna (Low)	Mistral Small 4 (Reasoning)	Difference
Intelligence (higher is better)	21.5	11.3	−47.4% Mistral Small 4 (Reas… is 47.4% less intelligent
Total AA cost (lower is better)	$10.63	$42.50	+299.8% Mistral Small 4 (Reas… is 4.0× more expensive
End-to-end time (lower is better)	6.80s	14.95s	+119.9% Mistral Small 4 (Reas… is 119.9% slower
Price per 1M tokens (in / out)	$0.10 / $0.50	$0.15 / $0.60
Input modalities	Text, Image	Text, Image

Open this matchup in the interactive picker GPT-6 Luna (Low): what beats it Mistral Small 4 (Reasoning): what beats it

Today's Pareto frontier

Against the frontier

GPT-6 Luna (Low) is on today's frontier: nothing is both smarter and cheaper.
Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.

GPT-6 Luna (Low)Mistral Small 4 (Reasoning)Today'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-low/mistral-small-4 · Markdown: /api/v1/compare/gpt-6-luna-low/mistral-small-4?format=md · llms.txt · agent skill