GPT-6 Luna (High) vs Mistral Small 3.1
Which is better for the money: GPT-6 Luna (High) by OpenAI or Mistral Small 3.1 by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
GPT-6 Luna (High) scores 25.8 points higher (32.9 vs 7.1) but costs 1.7× as much to run the benchmark ($47.9 vs $27.8; both budget class). Pick GPT-6 Luna (High) when the extra intelligence is worth the premium, otherwise Mistral Small 3.1.
| Metric | GPT-6 Luna (High) | Mistral Small 3.1 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 32.9 | 7.1 | −78.4% Mistral Small 3.1 is 78.4% less intelligent |
| Total AA cost (lower is better) | $47.85 | $27.82 | −41.9% Mistral Small 3.1 is 41.9% cheaper |
| End-to-end time (lower is better) | 18.94s | 10.74s | −43.3% Mistral Small 3.1 is 43.3% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.08 / $0.14 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 3.1 vs GPT-6 Luna (High): 78.4% less intelligence, 41.9% less cost to run the AA benchmark, and 43.3% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (High) is on today's frontier: nothing is both smarter and cheaper.
- Mistral Small 3.1 is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
GPT-6 Luna (High)Mistral Small 3.1Today'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-high/mistral-small-3-1 · Markdown: /api/v1/compare/gpt-6-luna-high/mistral-small-3-1?format=md · llms.txt · agent skill