DeepSeek V4 Pro 0813 (Non-reasoning) vs Ministral 3 8B
Which is better for the money: DeepSeek V4 Pro 0813 (Non-reasoning) by DeepSeek or Ministral 3 8B 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
DeepSeek V4 Pro 0813 (Non-reasoning) scores 14.9 points higher (20.4 vs 5.5) but costs 16× as much to run the benchmark ($451 vs $27.5; mid-range vs budget cost classes). They are not alternatives at one budget: pick DeepSeek V4 Pro 0813 (Non-reasoning) when you need intelligence above 5.5, and Ministral 3 8B when 5.5 is enough.
| Metric | DeepSeek V4 Pro 0813 (Non-reasoning) | Ministral 3 8B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.4 | 5.5 | −73.0% Ministral 3 8B is 73.0% less intelligent |
| Total AA cost (lower is better) | $450.76 | $27.47 | −93.9% Ministral 3 8B is 93.9% cheaper |
| End-to-end time (lower is better) | 6.81s | 5.40s | −20.7% Ministral 3 8B is 20.7% faster |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $0.15 / $0.15 | |
| Input modalities | Text | Text, Image |
Ministral 3 8B vs DeepSeek V4 Pro 0813 (Non-reasoning): 73.0% less intelligence, 93.9% less cost to run the AA benchmark, and 20.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro 0813 (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- Ministral 3 8B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
DeepSeek V4 Pro 0813 (Non-reasoning)Ministral 3 8BToday'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-v4-pro-non-reasoning/ministral-3-8b · Markdown: /api/v1/compare/deepseek-v4-pro-non-reasoning/ministral-3-8b?format=md · llms.txt · agent skill