DeepSeek V4.1 Flash 1017 (Max) vs Mistral Small 4 (Reasoning)

Which is better for the money: DeepSeek V4.1 Flash 1017 (Max) by DeepSeek 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.

Trade-off

DeepSeekDeepSeek V4.1 Flash 1017 (Max)Off the frontier

Intelligence: 45.10
Total cost: $445

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

Intelligence: 11.30
Total cost: $42.5

Verdict

Depends on your budget

DeepSeek V4.1 Flash 1017 (Max) scores 33.8 points higher (45.1 vs 11.3) but costs 10× as much to run the benchmark ($445 vs $42.5; mid-range vs budget cost classes). They are not alternatives at one budget: pick DeepSeek V4.1 Flash 1017 (Max) when you need intelligence above 11.3, and Mistral Small 4 (Reasoning) when 11.3 is enough.

Metric	DeepSeek V4.1 Flash 1017 (Max)	Mistral Small 4 (Reasoning)	Difference
Intelligence (higher is better)	45.1	11.3	−74.9% Mistral Small 4 (Reas… is 74.9% less intelligent
Total AA cost (lower is better)	$444.60	$42.50	−90.4% Mistral Small 4 (Reas… is 90.4% cheaper
End-to-end time (lower is better)	15.97s	14.77s	−7.5% Mistral Small 4 (Reas… is 7.5% faster
Price per 1M tokens (in / out)	$0.30 / $1.20	$0.15 / $0.60
Input modalities	Text, Image	Text, Image

Mistral Small 4 (Reasoning) vs DeepSeek V4.1 Flash 1017 (Max): 74.9% less intelligence, 90.4% less cost to run the AA benchmark, and 7.5% faster end-to-end.

Open this matchup in the interactive picker DeepSeek V4.1 Flash 1017 (Max): what beats it Mistral Small 4 (Reasoning): what beats it

Today's Pareto frontier

Against the frontier

DeepSeek V4.1 Flash 1017 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.

DeepSeek V4.1 Flash 1017 (Max)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/deepseek-v4-1-flash-1017/mistral-small-4 · Markdown: /api/v1/compare/deepseek-v4-1-flash-1017/mistral-small-4?format=md · llms.txt · agent skill