DeepSeek V4.1 Flash 1017 (Max) vs GPT-6 Luna (Non-reasoning)
Which is better for the money: DeepSeek V4.1 Flash 1017 (Max) by DeepSeek or GPT-6 Luna (Non-reasoning) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
DeepSeek V4.1 Flash 1017 (Max) scores 26.6 points higher (45.1 vs 18.5) but costs 23× as much to run the benchmark ($445 vs $19.2; 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 18.5, and GPT-6 Luna (Non-reasoning) when 18.5 is enough.
| Metric | DeepSeek V4.1 Flash 1017 (Max) | GPT-6 Luna (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 45.1 | 18.5 | −59.0% GPT-6 Luna (Non-reaso… is 59.0% less intelligent |
| Total AA cost (lower is better) | $444.60 | $19.16 | −95.7% GPT-6 Luna (Non-reaso… is 95.7% cheaper |
| End-to-end time (lower is better) | 15.82s | 5.05s | −68.1% GPT-6 Luna (Non-reaso… is 68.1% faster |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
GPT-6 Luna (Non-reasoning) vs DeepSeek V4.1 Flash 1017 (Max): 59.0% less intelligence, 95.7% less cost to run the AA benchmark, and 68.1% faster end-to-end.
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.
- GPT-6 Luna (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
DeepSeek V4.1 Flash 1017 (Max)GPT-6 Luna (Non-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/gpt-6-luna-non-reasoning · Markdown: /api/v1/compare/deepseek-v4-1-flash-1017/gpt-6-luna-non-reasoning?format=md · llms.txt · agent skill