DeepSeek V3 (Dec '24) vs GPT-6 Luna (Non-reasoning)
Which is better for the money: DeepSeek V3 (Dec '24) 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 2026-10-26.
Clear winner
Verdict
Pick GPT-6 Luna (Non-reasoning)
GPT-6 Luna (Non-reasoning) vs DeepSeek V3 (Dec '24): 117.6% more intelligence, 24.5% less cost to run the AA benchmark, and 58.8% faster end-to-end.
| Metric | DeepSeek V3 (Dec '24) | GPT-6 Luna (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 18.5 | +117.6% GPT-6 Luna (Non-reaso… is 2.2× more intelligent |
| Total AA cost (lower is better) | $25.37 | $19.16 | −24.5% GPT-6 Luna (Non-reaso… is 24.5% cheaper |
| End-to-end time (lower is better) | 12.35s | 5.09s | −58.8% GPT-6 Luna (Non-reaso… is 58.8% faster |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.10 / $0.50 | |
| Input modalities | Text | Text, Image |
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.
- 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 V3 (Dec '24)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-v3/gpt-6-luna-non-reasoning · Markdown: /api/v1/compare/deepseek-v3/gpt-6-luna-non-reasoning?format=md · llms.txt · agent skill