Mistral Large 4 Preview vs Solar Mini 4
Which is better for the money: Mistral Large 4 Preview by Mistral or Solar Mini 4 by Upstage? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Mistral Large 4 Preview scores 14.3 points higher (38.4 vs 24.1) but costs 3.2× as much to run the benchmark ($1608 vs $502; both premium class). They are not alternatives at one budget: pick Mistral Large 4 Preview when you need intelligence above 24.1, and Solar Mini 4 when 24.1 is enough.
| Metric | Mistral Large 4 Preview | Solar Mini 4 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 38.4 | 24.1 | −37.2% Solar Mini 4 is 37.2% less intelligent |
| Total AA cost (lower is better) | $1,607.86 | $502.02 | −68.8% Solar Mini 4 is 68.8% cheaper |
| End-to-end time (lower is better) | 25.73s | 27.46s | +6.7% Solar Mini 4 is 6.7% slower |
| Price per 1M tokens (in / out) | $1.36 / $4.18 | $0.10 / $0.40 | |
| Input modalities | Text, Image | Text |
Solar Mini 4 vs Mistral Large 4 Preview: 37.2% less intelligence, 68.8% less cost to run the AA benchmark, and 6.7% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Mistral Large 4 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- Solar Mini 4 is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
Mistral Large 4 PreviewSolar Mini 4Today's Pareto frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/mistral-large-4/solar-mini4 · Markdown: /api/v1/compare/mistral-large-4/solar-mini4?format=md · llms.txt · agent skill