gpt-oss-20b (High) vs Ministral 3 3B
Which is better for the money: gpt-oss-20b (High) by OpenAI or Ministral 3 3B by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
gpt-oss-20b (High) scores 4.2 points higher (9.0 vs 4.8) but costs 2.4× as much to run the benchmark ($28.8 vs $12.2; both budget class). Pick gpt-oss-20b (High) when the extra intelligence is worth the premium, otherwise Ministral 3 3B.
| Metric | gpt-oss-20b (High) | Ministral 3 3B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.0 | 4.8 | −46.7% Ministral 3 3B is 46.7% less intelligent |
| Total AA cost (lower is better) | $28.81 | $12.23 | −57.5% Ministral 3 3B is 57.5% cheaper |
| End-to-end time (lower is better) | 14.42s | 3.07s | −78.7% Ministral 3 3B is 78.7% faster |
| Price per 1M tokens (in / out) | $0.05 / $0.22 | $0.10 / $0.10 | |
| Input modalities | Text | Text, Image |
Ministral 3 3B vs gpt-oss-20b (High): 46.7% less intelligence, 57.5% less cost to run the AA benchmark, and 78.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Ministral 3 3B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
gpt-oss-20b (High)Ministral 3 3BToday'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-oss-20b/ministral-3-3b · Markdown: /api/v1/compare/gpt-oss-20b/ministral-3-3b?format=md · llms.txt · agent skill