DeepSeek R1 (Jan '25) vs MiniMax-M3.1-Flash
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or MiniMax-M3.1-Flash by MiniMax? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Clear winner
Verdict
Pick MiniMax-M3.1-Flash
MiniMax-M3.1-Flash vs DeepSeek R1 (Jan '25): 274.6% more intelligence, 38.5% less cost to run the AA benchmark, and 13.0% slower end-to-end.
| Metric | DeepSeek R1 (Jan '25) | MiniMax-M3.1-Flash | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 42.7 | +274.6% MiniMax-M3.1-Flash is 3.7× more intelligent |
| Total AA cost (lower is better) | $460.74 | $283.18 | −38.5% MiniMax-M3.1-Flash is 38.5% cheaper |
| End-to-end time (lower is better) | 19.17s | 21.66s | +13.0% MiniMax-M3.1-Flash is 13.0% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $0.15 / $0.60 | |
| Input modalities | Text | Text, Image |
Today's Pareto frontier
Against the frontier
- DeepSeek R1 (Jan '25) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- MiniMax-M3.1-Flash is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
DeepSeek R1 (Jan '25)MiniMax-M3.1-FlashToday'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-r1-0120/minimax-m3-1-flash · Markdown: /api/v1/compare/deepseek-r1-0120/minimax-m3-1-flash?format=md · llms.txt · agent skill