GPT-6 Luna (Xhigh) vs Mistral Large 4 Preview
Which is better for the money: GPT-6 Luna (Xhigh) by OpenAI or Mistral Large 4 Preview by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-29.
Trade-off
Verdict
Depends on your budget
Mistral Large 4 Preview scores 2.0 points higher (25.3 vs 23.3) but costs 34× as much to run the benchmark ($2923 vs $85.7; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Mistral Large 4 Preview when you need intelligence above 23.3, and GPT-6 Luna (Xhigh) when 23.3 is enough.
| Metric | GPT-6 Luna (Xhigh) | Mistral Large 4 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 23.3 | 25.3 | +8.6% Mistral Large 4 Previ… is 8.6% more intelligent |
| Total AA cost (lower is better) | $85.74 | $2,923.39 | +3309.6% Mistral Large 4 Previ… is 34× more expensive |
| End-to-end time (lower is better) | 21.74s | 25.54s | +17.5% Mistral Large 4 Previ… is 17.5% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.70 / $2.10 | |
| Input modalities | Text, Image | Text, Image |
Mistral Large 4 Preview vs GPT-6 Luna (Xhigh): 8.6% more intelligence, 3309.6% more cost to run the AA benchmark, and 17.5% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Xhigh) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 24.60 for $72.7.
- Mistral Large 4 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 54.50 for $1124.
GPT-6 Luna (Xhigh)Mistral Large 4 PreviewToday'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/gpt-6-luna-xhigh/mistral-large-4-preview · Markdown: /api/v1/compare/gpt-6-luna-xhigh/mistral-large-4-preview?format=md · llms.txt · agent skill