GPT-6 Luna (Max) vs Mistral Small 4 (Reasoning)
Which is better for the money: GPT-6 Luna (Max) by OpenAI or Mistral Small 4 (Reasoning) by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
GPT-6 Luna (Max) scores 26.8 points higher (38.1 vs 11.3) but costs 2.9× as much to run the benchmark ($122 vs $42.5; mid-range vs budget cost classes). Pick GPT-6 Luna (Max) when the extra intelligence is worth the premium, otherwise Mistral Small 4 (Reasoning).
| Metric | GPT-6 Luna (Max) | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 38.1 | 11.3 | −70.3% Mistral Small 4 (Reas… is 70.3% less intelligent |
| Total AA cost (lower is better) | $122.05 | $42.50 | −65.2% Mistral Small 4 (Reas… is 65.2% cheaper |
| End-to-end time (lower is better) | 82.02s | 14.50s | −82.3% Mistral Small 4 (Reas… is 82.3% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.15 / $0.60 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 4 (Reasoning) vs GPT-6 Luna (Max): 70.3% less intelligence, 65.2% less cost to run the AA benchmark, and 82.3% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Max) is on today's frontier: nothing is both smarter and cheaper.
- Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
GPT-6 Luna (Max)Mistral Small 4 (Reasoning)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/gpt-6-luna/mistral-small-4 · Markdown: /api/v1/compare/gpt-6-luna/mistral-small-4?format=md · llms.txt · agent skill