GPT-6 Luna (Non-reasoning) vs Mistral Large 4 Preview
Which is better for the money: GPT-6 Luna (Non-reasoning) 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 15.9 points higher (25.3 vs 9.4) but costs 74× as much to run the benchmark ($3922 vs $53.1; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Mistral Large 4 Preview when you need intelligence above 9.4, and GPT-6 Luna (Non-reasoning) when 9.4 is enough.
| Metric | GPT-6 Luna (Non-reasoning) | Mistral Large 4 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.4 | 25.3 | +169.1% Mistral Large 4 Previ… is 2.7× more intelligent |
| Total AA cost (lower is better) | $53.14 | $3,922.39 | +7281.2% Mistral Large 4 Previ… is 74× more expensive |
| End-to-end time (lower is better) | 5.25s | 24.37s | +364.2% Mistral Large 4 Previ… is 364.2% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $1.36 / $4.18 | |
| Input modalities | Text, Image | Text, Image |
Mistral Large 4 Preview vs GPT-6 Luna (Non-reasoning): 169.1% more intelligence, 7281.2% more cost to run the AA benchmark, and 364.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- 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.
- Mistral Large 4 Preview is off the frontier: at the same or lower cost, GPT-6 Astra (Xhigh) scores 55.30 for $3746.
GPT-6 Luna (Non-reasoning)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-non-reasoning/mistral-large-4-preview · Markdown: /api/v1/compare/gpt-6-luna-non-reasoning/mistral-large-4-preview?format=md · llms.txt · agent skill