gpt-oss-20b (High) vs Mistral Medium 3.5
Which is better for the money: gpt-oss-20b (High) by OpenAI or Mistral Medium 3.5 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 Medium 3.5 scores 5.2 points higher (14.2 vs 9.0) but costs 44× as much to run the benchmark ($1264 vs $28.8; premium vs budget cost classes). They are not alternatives at one budget: pick Mistral Medium 3.5 when you need intelligence above 9.0, and gpt-oss-20b (High) when 9.0 is enough.
| Metric | gpt-oss-20b (High) | Mistral Medium 3.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.0 | 14.2 | +57.8% Mistral Medium 3.5 is 57.8% more intelligent |
| Total AA cost (lower is better) | $28.81 | $1,263.80 | +4286.7% Mistral Medium 3.5 is 44× more expensive |
| End-to-end time (lower is better) | 16.48s | 17.77s | +7.8% Mistral Medium 3.5 is 7.8% slower |
| Price per 1M tokens (in / out) | $0.05 / $0.22 | $1.50 / $7.50 | |
| Input modalities | Text | Text, Image |
Mistral Medium 3.5 vs gpt-oss-20b (High): 57.8% more intelligence, 4286.7% more cost to run the AA benchmark, and 7.8% slower 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.
- Mistral Medium 3.5 is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
gpt-oss-20b (High)Mistral Medium 3.5Today'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/mistral-medium-3-5 · Markdown: /api/v1/compare/gpt-oss-20b/mistral-medium-3-5?format=md · llms.txt · agent skill