Granite 4.2 3B vs Mistral Large 3
Which is better for the money: Granite 4.2 3B by IBM or Mistral Large 3 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 3 scores 0.2 points higher (9.3 vs 9.1) but costs 3.1× as much to run the benchmark ($46.4 vs $14.9; both budget class). They are not alternatives at one budget: pick Mistral Large 3 when you need intelligence above 9.1, and Granite 4.2 3B when 9.1 is enough.
| Metric | Granite 4.2 3B | Mistral Large 3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.1 | 9.3 | +2.2% Mistral Large 3 is 2.2% more intelligent |
| Total AA cost (lower is better) | $14.91 | $46.41 | +211.3% Mistral Large 3 is 3.1× more expensive |
| End-to-end time (lower is better) | 46.62s | 7.17s | −84.6% Mistral Large 3 is 84.6% faster |
| Price per 1M tokens (in / out) | $0.03 / $0.12 | $0.50 / $1.50 | |
| Input modalities | Text | Text, Image |
Mistral Large 3 vs Granite 4.2 3B: 2.2% more intelligence, 211.3% more cost to run the AA benchmark, and 84.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Granite 4.2 3B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Mistral Large 3 is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
Granite 4.2 3BMistral Large 3Today'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-4-2-3b/mistral-large-3 · Markdown: /api/v1/compare/granite-4-2-3b/mistral-large-3?format=md · llms.txt · agent skill