Mistral Small 4 (Reasoning) vs Nemotron 3 Super 120B A12B (Reasoning)
Which is better for the money: Mistral Small 4 (Reasoning) by Mistral or Nemotron 3 Super 120B A12B (Reasoning) by NVIDIA? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Depends on your budget
Nemotron 3 Super 120B A12B (Reasoning) scores 1.5 points higher (12.8 vs 11.3) but costs 31× as much to run the benchmark ($1319 vs $42.5; premium vs budget cost classes). They are not alternatives at one budget: pick Nemotron 3 Super 120B A12B (Reasoning) when you need intelligence above 11.3, and Mistral Small 4 (Reasoning) when 11.3 is enough.
| Metric | Mistral Small 4 (Reasoning) | Nemotron 3 Super 120B A12B (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.3 | 12.8 | +13.3% Nemotron 3 Super 120B… is 13.3% more intelligent |
| Total AA cost (lower is better) | $42.50 | $1,318.62 | +3002.6% Nemotron 3 Super 120B… is 31× more expensive |
| End-to-end time (lower is better) | 15.13s | 16.18s | +6.9% Nemotron 3 Super 120B… is 6.9% slower |
| Price per 1M tokens (in / out) | $0.15 / $0.60 | $0.30 / $0.90 | |
| Input modalities | Text, Image | Text |
Nemotron 3 Super 120B A12B (Reasoning) vs Mistral Small 4 (Reasoning): 13.3% more intelligence, 3002.6% more cost to run the AA benchmark, and 6.9% slower end-to-end.
Against the frontier
- Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
- Nemotron 3 Super 120B A12B (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Compare something else
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/mistral-small-4/nvidia-nemotron-3-super-120b-a12b · Markdown: /api/v1/compare/mistral-small-4/nvidia-nemotron-3-super-120b-a12b?format=md · llms.txt · agent skill