Gemini 4 Carbon (Medium) vs GPT-6 Luna (Non-reasoning)
Which is better for the money: Gemini 4 Carbon (Medium) by Google or GPT-6 Luna (Non-reasoning) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-11-03.
Trade-off
Verdict
Depends on your budget
Gemini 4 Carbon (Medium) scores 48.3 points higher (57.7 vs 9.4) but costs 111× as much to run the benchmark ($5903 vs $53.1; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 4 Carbon (Medium) when you need intelligence above 9.4, and GPT-6 Luna (Non-reasoning) when 9.4 is enough.
| Metric | Gemini 4 Carbon (Medium) | GPT-6 Luna (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 57.7 | 9.4 | −83.7% GPT-6 Luna (Non-reaso… is 83.7% less intelligent |
| Total AA cost (lower is better) | $5,903.03 | $53.14 | −99.1% GPT-6 Luna (Non-reaso… is 99.1% cheaper |
| End-to-end time (lower is better) | 11.62s | 5.37s | −53.8% GPT-6 Luna (Non-reaso… is 53.8% faster |
| Price per 1M tokens (in / out) | $4.00 / $20.0 | $0.10 / $0.50 | |
| Input modalities | Text, Image, Speech, Video | Text, Image |
GPT-6 Luna (Non-reasoning) vs Gemini 4 Carbon (Medium): 83.7% less intelligence, 99.1% less cost to run the AA benchmark, and 53.8% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 4 Carbon (Medium) is on today's frontier: nothing is both smarter and cheaper.
- GPT-6 Luna (Non-reasoning) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Low) scores 18.60 for $39.6.
Gemini 4 Carbon (Medium)GPT-6 Luna (Non-reasoning)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/gemini-4-carbon-medium/gpt-6-luna-non-reasoning · Markdown: /api/v1/compare/gemini-4-carbon-medium/gpt-6-luna-non-reasoning?format=md · llms.txt · agent skill