gpt-oss-20b (High) vs Mistral Small 4 (Reasoning)
Which is better for the money: gpt-oss-20b (High) by OpenAI or Mistral Small 4 (Reasoning) 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 Small 4 (Reasoning) scores 2.3 points higher (11.3 vs 9.0) but costs 1.5× as much to run the benchmark ($42.5 vs $28.8; both budget class). Pick Mistral Small 4 (Reasoning) when the extra intelligence is worth the premium, otherwise gpt-oss-20b (High).
| Metric | gpt-oss-20b (High) | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.0 | 11.3 | +25.6% Mistral Small 4 (Reas… is 25.6% more intelligent |
| Total AA cost (lower is better) | $28.81 | $42.50 | +47.5% Mistral Small 4 (Reas… is 47.5% more expensive |
| End-to-end time (lower is better) | 16.79s | 14.50s | −13.6% Mistral Small 4 (Reas… is 13.6% faster |
| Price per 1M tokens (in / out) | $0.05 / $0.22 | $0.15 / $0.60 | |
| Input modalities | Text | Text, Image |
Mistral Small 4 (Reasoning) vs gpt-oss-20b (High): 25.6% more intelligence, 47.5% more cost to run the AA benchmark, and 13.6% 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.
- Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
gpt-oss-20b (High)Mistral Small 4 (Reasoning)Today'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-small-4 · Markdown: /api/v1/compare/gpt-oss-20b/mistral-small-4?format=md · llms.txt · agent skill