DeepSeek V4 Pro 0813 (Max) vs MiniMax-M3
Which is better for the money: DeepSeek V4 Pro 0813 (Max) by DeepSeek or MiniMax-M3 by MiniMax? 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 (Max) scores 6.8 points higher (36.0 vs 29.2) but costs 2.1× as much to run the benchmark ($1122 vs $538; both premium class). Pick DeepSeek V4 Pro 0813 (Max) when the extra intelligence is worth the premium, otherwise MiniMax-M3.
| Metric | DeepSeek V4 Pro 0813 (Max) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 36.0 | 29.2 | −18.9% MiniMax-M3 is 18.9% less intelligent |
| Total AA cost (lower is better) | $1,122.27 | $537.98 | −52.1% MiniMax-M3 is 52.1% cheaper |
| End-to-end time (lower is better) | 25.78s | 26.74s | +3.7% MiniMax-M3 is 3.7% slower |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $0.30 / $1.20 | |
| Input modalities | Text | Text, Image, Video |
MiniMax-M3 vs DeepSeek V4 Pro 0813 (Max): 18.9% less intelligence, 52.1% less cost to run the AA benchmark, and 3.7% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro 0813 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
DeepSeek V4 Pro 0813 (Max)MiniMax-M3Today'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/minimax-m3 · Markdown: /api/v1/compare/deepseek-v4-pro/minimax-m3?format=md · llms.txt · agent skill