DeepSeek V3 (Dec '24) vs Mistral Small 4 (Reasoning)
Which is better for the money: DeepSeek V3 (Dec '24) by DeepSeek 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 2.8 points higher (11.3 vs 8.5) but costs 1.7× as much to run the benchmark ($42.5 vs $25.4; both budget class). Pick Mistral Small 4 (Reasoning) when the extra intelligence is worth the premium, otherwise DeepSeek V3 (Dec '24).
| Metric | DeepSeek V3 (Dec '24) | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 11.3 | +32.9% Mistral Small 4 (Reas… is 32.9% more intelligent |
| Total AA cost (lower is better) | $25.37 | $42.50 | +67.5% Mistral Small 4 (Reas… is 67.5% more expensive |
| End-to-end time (lower is better) | 11.89s | 14.50s | +22.0% Mistral Small 4 (Reas… is 22.0% slower |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.15 / $0.60 | |
| Input modalities | Text | Text, Image |
Mistral Small 4 (Reasoning) vs DeepSeek V3 (Dec '24): 32.9% more intelligence, 67.5% more cost to run the AA benchmark, and 22.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V3 (Dec '24) 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.
DeepSeek V3 (Dec '24)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/deepseek-v3/mistral-small-4 · Markdown: /api/v1/compare/deepseek-v3/mistral-small-4?format=md · llms.txt · agent skill