GPT-6.1 Terra (High) vs Mistral Small 3.2
Which is better for the money: GPT-6.1 Terra (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 2026-10-27.
Trade-off
Verdict
Depends on your budget
GPT-6.1 Terra (High) scores 36.9 points higher (43.9 vs 7.0) but costs 2.0× as much to run the benchmark ($239 vs $122; both mid-range class). Pick GPT-6.1 Terra (High) when the extra intelligence is worth the premium, otherwise Mistral Small 3.2.
| Metric | GPT-6.1 Terra (High) | Mistral Small 3.2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.9 | 7.0 | −84.1% Mistral Small 3.2 is 84.1% less intelligent |
| Total AA cost (lower is better) | $238.53 | $121.78 | −48.9% Mistral Small 3.2 is 48.9% cheaper |
| End-to-end time (lower is better) | 11.16s | 10.54s | −5.6% Mistral Small 3.2 is 5.6% faster |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $0.07 / $0.20 | |
| Input modalities | Text, Image | Text, Image |
Mistral Small 3.2 vs GPT-6.1 Terra (High): 84.1% less intelligence, 48.9% less cost to run the AA benchmark, and 5.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Terra (High) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Mistral Small 3.2 is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
GPT-6.1 Terra (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-6-1-terra-high/mistral-small-3-2 · Markdown: /api/v1/compare/gpt-6-1-terra-high/mistral-small-3-2?format=md · llms.txt · agent skill