Celeris-1 vs Mistral Large 4 Preview
Which is better for the money: Celeris-1 by Celeris or Mistral Large 4 Preview 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
Mistral Large 4 Preview scores 32.1 points higher (38.4 vs 6.3) but costs 27× as much to run the benchmark ($1608 vs $60.0; premium vs mid-range cost classes). They are not alternatives at one budget: pick Mistral Large 4 Preview when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | Mistral Large 4 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 38.4 | +509.5% Mistral Large 4 Previ… is 6.1× more intelligent |
| Total AA cost (lower is better) | $59.99 | $1,607.86 | +2580.2% Mistral Large 4 Previ… is 27× more expensive |
| End-to-end time (lower is better) | 0.87s | 27.12s | +3017.2% Mistral Large 4 Previ… is 3017.2% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $1.36 / $4.18 | |
| Input modalities | Text, Image | Text, Image |
Mistral Large 4 Preview vs Celeris-1: 509.5% more intelligence, 2580.2% more cost to run the AA benchmark, and 3017.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Celeris-1 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
- Mistral Large 4 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Celeris-1Mistral Large 4 PreviewToday'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/celeris-1/mistral-large-4 · Markdown: /api/v1/compare/celeris-1/mistral-large-4?format=md · llms.txt · agent skill