DeepSeek V4 Flash 0731 (Max) vs Mistral Medium 3.5

Which is better for the money: DeepSeek V4 Flash 0731 (Max) by DeepSeek or Mistral Medium 3.5 by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.

Clear winner

DeepSeekDeepSeek V4 Flash 0731 (Max)Off the frontier

Intelligence: 34.30
Total cost: $200

MistralMistral Medium 3.5Off the frontier

Intelligence: 14.20
Total cost: $1264

Verdict

Pick DeepSeek V4 Flash 0731 (Max)

Mistral Medium 3.5 vs DeepSeek V4 Flash 0731 (Max): 58.6% less intelligence, 533.1% more cost to run the AA benchmark, and 0.2% slower end-to-end.

Metric	DeepSeek V4 Flash 0731 (Max)	Mistral Medium 3.5	Difference
Intelligence (higher is better)	34.3	14.2	−58.6% Mistral Medium 3.5 is 58.6% less intelligent
Total AA cost (lower is better)	$199.63	$1,263.80	+533.1% Mistral Medium 3.5 is 6.3× more expensive
End-to-end time (lower is better)	17.63s	17.66s	+0.2% Mistral Medium 3.5 is 0.2% slower
Price per 1M tokens (in / out)	$0.14 / $0.28	$1.50 / $7.50
Input modalities	Text	Text, Image

Open this matchup in the interactive picker DeepSeek V4 Flash 0731 (Max): what beats it Mistral Medium 3.5: what beats it

Today's Pareto frontier

Against the frontier

DeepSeek V4 Flash 0731 (Max) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
Mistral Medium 3.5 is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.

DeepSeek V4 Flash 0731 (Max)Mistral Medium 3.5Today'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-flash/mistral-medium-3-5 · Markdown: /api/v1/compare/deepseek-v4-flash/mistral-medium-3-5?format=md · llms.txt · agent skill