DeepSeek V4 Flash 0420 (Max) vs Mistral Large 3
Which is better for the money: DeepSeek V4 Flash 0420 (Max) by DeepSeek or Mistral Large 3 by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
DeepSeek V4 Flash 0420 (Max) scores 14.9 points higher (24.2 vs 9.3) but costs 3.2× as much to run the benchmark ($149 vs $46.4; mid-range vs budget cost classes). They are not alternatives at one budget: pick DeepSeek V4 Flash 0420 (Max) when you need intelligence above 9.3, and Mistral Large 3 when 9.3 is enough.
| Metric | DeepSeek V4 Flash 0420 (Max) | Mistral Large 3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 24.2 | 9.3 | −61.6% Mistral Large 3 is 61.6% less intelligent |
| Total AA cost (lower is better) | $149.48 | $46.41 | −69.0% Mistral Large 3 is 69.0% cheaper |
| End-to-end time (lower is better) | 107.06s | 7.23s | −93.2% Mistral Large 3 is 93.2% faster |
| Price per 1M tokens (in / out) | $0.11 / $0.23 | $0.50 / $1.50 | |
| Input modalities | Text | Text, Image |
Mistral Large 3 vs DeepSeek V4 Flash 0420 (Max): 61.6% less intelligence, 69.0% less cost to run the AA benchmark, and 93.2% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Flash 0420 (Max) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
- Mistral Large 3 is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
DeepSeek V4 Flash 0420 (Max)Mistral Large 3Today'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-flash-0420/mistral-large-3 · Markdown: /api/v1/compare/deepseek-v4-flash-0420/mistral-large-3?format=md · llms.txt · agent skill