GPT-5.6 Luna (Max) vs Mistral Small 3.2
Which is better for the money: GPT-5.6 Luna (Max) by OpenAI or Mistral Small 3.2 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-5.6 Luna (Max) scores 30.3 points higher (37.3 vs 7.0) but costs 2.6× as much to run the benchmark ($320 vs $122; both mid-range class). Pick GPT-5.6 Luna (Max) when the extra intelligence is worth the premium, otherwise Mistral Small 3.2.
| Metric | GPT-5.6 Luna (Max) | Mistral Small 3.2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 37.3 | 7.0 | −81.2% Mistral Small 3.2 is 81.2% less intelligent |
| Total AA cost (lower is better) | $319.93 | $121.78 | −61.9% Mistral Small 3.2 is 61.9% cheaper |
| End-to-end time (lower is better) | 85.38s | 12.50s | −85.4% Mistral Small 3.2 is 85.4% faster |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $0.07 / $0.20 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 3.2 vs GPT-5.6 Luna (Max): 81.2% less intelligence, 61.9% less cost to run the AA benchmark, and 85.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (Max) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Mistral Small 3.2 is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
GPT-5.6 Luna (Max)Mistral Small 3.2Today'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-5-6-luna/mistral-small-3-2 · Markdown: /api/v1/compare/gpt-5-6-luna/mistral-small-3-2?format=md · llms.txt · agent skill