DeepSeek V4 Pro 0813 (Max) vs GPT-5.6 Luna (Low)
Which is better for the money: DeepSeek V4 Pro 0813 (Max) by DeepSeek or GPT-5.6 Luna (Low) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
DeepSeek V4 Pro 0813 (Max) scores 15.0 points higher (36.0 vs 21.0) but costs 42× as much to run the benchmark ($1122 vs $27.0; premium vs budget cost classes). They are not alternatives at one budget: pick DeepSeek V4 Pro 0813 (Max) when you need intelligence above 21.0, and GPT-5.6 Luna (Low) when 21.0 is enough.
| Metric | DeepSeek V4 Pro 0813 (Max) | GPT-5.6 Luna (Low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 36.0 | 21.0 | −41.7% GPT-5.6 Luna (Low) is 41.7% less intelligent |
| Total AA cost (lower is better) | $1,122.27 | $27.02 | −97.6% GPT-5.6 Luna (Low) is 97.6% cheaper |
| End-to-end time (lower is better) | 26.66s | 5.84s | −78.1% GPT-5.6 Luna (Low) is 78.1% faster |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $0.20 / $1.20 | |
| Input modalities | Text | Text, Image |
GPT-5.6 Luna (Low) vs DeepSeek V4 Pro 0813 (Max): 41.7% less intelligence, 97.6% less cost to run the AA benchmark, and 78.1% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro 0813 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- GPT-5.6 Luna (Low) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
DeepSeek V4 Pro 0813 (Max)GPT-5.6 Luna (Low)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-pro/gpt-5-6-luna-low · Markdown: /api/v1/compare/deepseek-v4-pro/gpt-5-6-luna-low?format=md · llms.txt · agent skill