GPT-6 Luna (Medium) vs Kimi K3 (Max)

Which is better for the money: GPT-6 Luna (Medium) by OpenAI 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

OpenAIGPT-6 Luna (Medium)On the frontier

Intelligence: 29.90
Total cost: $31.2

KimiKimi K3 (Max)Off the frontier

Intelligence: 43.60
Total cost: $3658

Verdict

Depends on your budget

Kimi K3 (Max) scores 13.7 points higher (43.6 vs 29.9) but costs 117× as much to run the benchmark ($3658 vs $31.2; flagship vs budget cost classes). They are not alternatives at one budget: pick Kimi K3 (Max) when you need intelligence above 29.9, and GPT-6 Luna (Medium) when 29.9 is enough.

Metric	GPT-6 Luna (Medium)	Kimi K3 (Max)	Difference
Intelligence (higher is better)	29.9	43.6	+45.8% Kimi K3 (Max) is 45.8% more intelligent
Total AA cost (lower is better)	$31.17	$3,658.07	+11635.9% Kimi K3 (Max) is 117× more expensive
End-to-end time (lower is better)	8.25s	56.93s	+590.1% Kimi K3 (Max) is 590.1% slower
Price per 1M tokens (in / out)	$0.10 / $0.50	$3.00 / $15.0
Input modalities	Text, Image	Text, Image

Kimi K3 (Max) vs GPT-6 Luna (Medium): 45.8% more intelligence, 11635.9% more cost to run the AA benchmark, and 590.1% slower end-to-end.

Open this matchup in the interactive picker GPT-6 Luna (Medium): what beats it Kimi K3 (Max): what beats it

Today's Pareto frontier

Against the frontier

GPT-6 Luna (Medium) is on today's frontier: nothing is both smarter and cheaper.
Kimi K3 (Max) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.

GPT-6 Luna (Medium)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/gpt-6-luna-medium/kimi-k3 · Markdown: /api/v1/compare/gpt-6-luna-medium/kimi-k3?format=md · llms.txt · agent skill