DeepSeek V4 Flash Vision (Max) vs GPT-6 Luna (Max)
Which is better for the money: DeepSeek V4 Flash Vision (Max) by DeepSeek or GPT-6 Luna (Max) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick GPT-6 Luna (Max)
GPT-6 Luna (Max) vs DeepSeek V4 Flash Vision (Max): 9.5% more intelligence, 88.7% less cost to run the AA benchmark, and 439.1% slower end-to-end.
| Metric | DeepSeek V4 Flash Vision (Max) | GPT-6 Luna (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.8 | 38.1 | +9.5% GPT-6 Luna (Max) is 9.5% more intelligent |
| Total AA cost (lower is better) | $1,081.42 | $122.05 | −88.7% GPT-6 Luna (Max) is 88.7% cheaper |
| End-to-end time (lower is better) | 16.10s | 86.79s | +439.1% GPT-6 Luna (Max) is 439.1% slower |
| Price per 1M tokens (in / out) | $0.44 / $1.32 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Flash Vision (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
- GPT-6 Luna (Max) is on today's frontier: nothing is both smarter and cheaper.
DeepSeek V4 Flash Vision (Max)GPT-6 Luna (Max)Today's Pareto 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-flash-vision/gpt-6-luna · Markdown: /api/v1/compare/deepseek-v4-flash-vision/gpt-6-luna?format=md · llms.txt · agent skill