DeepSeek V3 (Dec '24) vs GPT-6 Luna (Medium)
Which is better for the money: DeepSeek V3 (Dec '24) by DeepSeek or GPT-6 Luna (Medium) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
GPT-6 Luna (Medium) scores 21.4 points higher (29.9 vs 8.5) but costs 1.2× as much to run the benchmark ($31.2 vs $25.4; both budget class). Pick GPT-6 Luna (Medium) when the extra intelligence is worth the premium, otherwise DeepSeek V3 (Dec '24).
| Metric | DeepSeek V3 (Dec '24) | GPT-6 Luna (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 29.9 | +251.8% GPT-6 Luna (Medium) is 3.5× more intelligent |
| Total AA cost (lower is better) | $25.37 | $31.17 | +22.9% GPT-6 Luna (Medium) is 22.9% more expensive |
| End-to-end time (lower is better) | 10.23s | 8.25s | −19.4% GPT-6 Luna (Medium) is 19.4% faster |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.10 / $0.50 | |
| Input modalities | Text | Text, Image |
GPT-6 Luna (Medium) vs DeepSeek V3 (Dec '24): 251.8% more intelligence, 22.9% more cost to run the AA benchmark, and 19.4% faster end-to-end.
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 (Medium) is on today's frontier: nothing is both smarter and cheaper.
DeepSeek V3 (Dec '24)GPT-6 Luna (Medium)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-medium · Markdown: /api/v1/compare/deepseek-v3/gpt-6-luna-medium?format=md · llms.txt · agent skill