GPT-5.6 Luna (High) vs Mistral Small 3.2
Which is better for the money: GPT-5.6 Luna (High) by OpenAI or Mistral Small 3.2 by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Clear winner
Verdict
Pick GPT-5.6 Luna (High)
Mistral Small 3.2 vs GPT-5.6 Luna (High): 78.2% less intelligence, 12.6% more cost to run the AA benchmark, and 28.8% faster end-to-end.
| Metric | GPT-5.6 Luna (High) | Mistral Small 3.2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 32.1 | 7.0 | −78.2% Mistral Small 3.2 is 78.2% less intelligent |
| Total AA cost (lower is better) | $108.15 | $121.78 | +12.6% Mistral Small 3.2 is 12.6% more expensive |
| End-to-end time (lower is better) | 13.41s | 9.55s | −28.8% Mistral Small 3.2 is 28.8% faster |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $0.07 / $0.20 | |
| Input modalities | Text, Image | Text, Image |
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
- 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 (High)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-high/mistral-small-3-2 · Markdown: /api/v1/compare/gpt-5-6-luna-high/mistral-small-3-2?format=md · llms.txt · agent skill