Granite 4.2 30B vs Mistral Large 4 Preview
Which is better for the money: Granite 4.2 30B by IBM or Mistral Large 4 Preview by Mistral? 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 25.7 points higher (38.4 vs 12.7) but costs 15× as much to run the benchmark ($1608 vs $111; premium vs mid-range cost classes). They are not alternatives at one budget: pick Mistral Large 4 Preview when you need intelligence above 12.7, and Granite 4.2 30B when 12.7 is enough.
| Metric | Granite 4.2 30B | Mistral Large 4 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 12.7 | 38.4 | +202.4% Mistral Large 4 Previ… is 3.0× more intelligent |
| Total AA cost (lower is better) | $110.83 | $1,607.86 | +1350.7% Mistral Large 4 Previ… is 15× more expensive |
| End-to-end time (lower is better) | 55.20s | 24.31s | −56.0% Mistral Large 4 Previ… is 56.0% faster |
| Price per 1M tokens (in / out) | $0.16 / $0.65 | $1.36 / $4.18 | |
| Input modalities | Text | Text, Image |
Mistral Large 4 Preview vs Granite 4.2 30B: 202.4% more intelligence, 1350.7% more cost to run the AA benchmark, and 56.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Granite 4.2 30B is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
- Mistral Large 4 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Granite 4.2 30BMistral Large 4 PreviewToday'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/granite-4-2-30b/mistral-large-4 · Markdown: /api/v1/compare/granite-4-2-30b/mistral-large-4?format=md · llms.txt · agent skill