Mistral Small 3.2 vs Nemotron 3.5 Super VL
Which is better for the money: Mistral Small 3.2 by Mistral or Nemotron 3.5 Super VL by NVIDIA? 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
Nemotron 3.5 Super VL scores 19.5 points higher (26.5 vs 7.0) but costs 2.3× as much to run the benchmark ($286 vs $122; both mid-range class). Pick Nemotron 3.5 Super VL when the extra intelligence is worth the premium, otherwise Mistral Small 3.2.
| Metric | Mistral Small 3.2 | Nemotron 3.5 Super VL | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 7.0 | 26.5 | +278.6% Nemotron 3.5 Super VL is 3.8× more intelligent |
| Total AA cost (lower is better) | $121.78 | $286.07 | +134.9% Nemotron 3.5 Super VL is 2.3× more expensive |
| End-to-end time (lower is better) | 9.82s | 6.31s | −35.7% Nemotron 3.5 Super VL is 35.7% faster |
| Price per 1M tokens (in / out) | $0.07 / $0.20 | $0.23 / $0.57 | |
| Input modalities | Text, Image | Text, Image |
Nemotron 3.5 Super VL vs Mistral Small 3.2: 278.6% more intelligence, 134.9% more cost to run the AA benchmark, and 35.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Mistral Small 3.2 is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
- Nemotron 3.5 Super VL is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Mistral Small 3.2Nemotron 3.5 Super VLToday'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/mistral-small-3-2/nemotron-3-5-super-vl · Markdown: /api/v1/compare/mistral-small-3-2/nemotron-3-5-super-vl?format=md · llms.txt · agent skill