GPT-5.6 Luna (Non-reasoning) vs Mistral Small 4 (Reasoning)
Which is better for the money: GPT-5.6 Luna (Non-reasoning) 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.
Clear winner
Verdict
Pick GPT-5.6 Luna (Non-reasoning)
Mistral Small 4 (Reasoning) vs GPT-5.6 Luna (Non-reasoning): 27.1% less intelligence, 85.0% more cost to run the AA benchmark, and 204.6% slower end-to-end.
| Metric | GPT-5.6 Luna (Non-reasoning) | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 15.5 | 11.3 | −27.1% Mistral Small 4 (Reas… is 27.1% less intelligent |
| Total AA cost (lower is better) | $22.97 | $42.50 | +85.0% Mistral Small 4 (Reas… is 85.0% more expensive |
| End-to-end time (lower is better) | 4.76s | 14.50s | +204.6% Mistral Small 4 (Reas… is 204.6% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $0.15 / $0.60 | |
| Input modalities | Text, Image | Text, Image |
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- 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-5.6 Luna (Non-reasoning)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-5-6-luna-non-reasoning/mistral-small-4 · Markdown: /api/v1/compare/gpt-5-6-luna-non-reasoning/mistral-small-4?format=md · llms.txt · agent skill