gpt-oss-120b (High) vs Mistral Small 3.2
Which is better for the money: gpt-oss-120b (High) by OpenAI or Mistral Small 3.2 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
gpt-oss-120b (High) scores 4.6 points higher (11.6 vs 7.0) but costs 1.0× as much to run the benchmark ($123 vs $122; both mid-range class). Pick gpt-oss-120b (High) when the extra intelligence is worth the premium, otherwise Mistral Small 3.2.
| Metric | gpt-oss-120b (High) | Mistral Small 3.2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.6 | 7.0 | −39.7% Mistral Small 3.2 is 39.7% less intelligent |
| Total AA cost (lower is better) | $122.71 | $121.78 | −0.8% Mistral Small 3.2 is 0.8% cheaper |
| End-to-end time (lower is better) | 12.38s | 12.50s | +1.0% Mistral Small 3.2 is 1.0% slower |
| Price per 1M tokens (in / out) | $0.15 / $0.60 | $0.07 / $0.20 | |
| Input modalities | Text | Text, Image |
Mistral Small 3.2 vs gpt-oss-120b (High): 39.7% less intelligence, 0.8% less cost to run the AA benchmark, and 1.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-120b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
- Mistral Small 3.2 is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
gpt-oss-120b (High)Mistral Small 3.2Today'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-120b/mistral-small-3-2 · Markdown: /api/v1/compare/gpt-oss-120b/mistral-small-3-2?format=md · llms.txt · agent skill