DeepSeek V3 (Dec '24) vs Kimi K3 (Max)

Which is better for the money: DeepSeek V3 (Dec '24) by DeepSeek or Kimi K3 (Max) by Kimi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.

Trade-off

DeepSeekDeepSeek V3 (Dec '24)Off the frontier

Intelligence: 8.50
Total cost: $25.4

KimiKimi K3 (Max)Off the frontier

Intelligence: 43.60
Total cost: $3658

Verdict

Depends on your budget

Kimi K3 (Max) scores 35.1 points higher (43.6 vs 8.5) but costs 144× as much to run the benchmark ($3658 vs $25.4; flagship vs budget cost classes). They are not alternatives at one budget: pick Kimi K3 (Max) when you need intelligence above 8.5, and DeepSeek V3 (Dec '24) when 8.5 is enough.

Metric	DeepSeek V3 (Dec '24)	Kimi K3 (Max)	Difference
Intelligence (higher is better)	8.5	43.6	+412.9% Kimi K3 (Max) is 5.1× more intelligent
Total AA cost (lower is better)	$25.37	$3,658.07	+14318.9% Kimi K3 (Max) is 144× more expensive
End-to-end time (lower is better)	10.23s	56.93s	+456.5% Kimi K3 (Max) is 456.5% slower
Price per 1M tokens (in / out)	$0.32 / $0.89	$3.00 / $15.0
Input modalities	Text	Text, Image

Kimi K3 (Max) vs DeepSeek V3 (Dec '24): 412.9% more intelligence, 14318.9% more cost to run the AA benchmark, and 456.5% slower end-to-end.

Open this matchup in the interactive picker DeepSeek V3 (Dec '24): what beats it Kimi K3 (Max): what beats it

Today's Pareto frontier

Against the frontier

DeepSeek V3 (Dec '24) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Kimi K3 (Max) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.

DeepSeek V3 (Dec '24)Kimi K3 (Max)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-v3/kimi-k3 · Markdown: /api/v1/compare/deepseek-v3/kimi-k3?format=md · llms.txt · agent skill