Mercury 2.5 vs MiniMax-M3.1-Flash
Which is better for the money: Mercury 2.5 by Inception or MiniMax-M3.1-Flash by MiniMax? 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
MiniMax-M3.1-Flash scores 30.4 points higher (42.7 vs 12.3) but costs 1.3× as much to run the benchmark ($283 vs $218; both mid-range class). Pick MiniMax-M3.1-Flash when the extra intelligence is worth the premium, otherwise Mercury 2.5.
| Metric | Mercury 2.5 | MiniMax-M3.1-Flash | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 12.3 | 42.7 | +247.2% MiniMax-M3.1-Flash is 3.5× more intelligent |
| Total AA cost (lower is better) | $218.11 | $283.18 | +29.8% MiniMax-M3.1-Flash is 29.8% more expensive |
| End-to-end time (lower is better) | 4.18s | 22.73s | +443.8% MiniMax-M3.1-Flash is 443.8% slower |
| Price per 1M tokens (in / out) | $0.25 / $0.75 | $0.15 / $0.60 | |
| Input modalities | Text | Text, Image |
MiniMax-M3.1-Flash vs Mercury 2.5: 247.2% more intelligence, 29.8% more cost to run the AA benchmark, and 443.8% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Mercury 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- MiniMax-M3.1-Flash is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Mercury 2.5MiniMax-M3.1-FlashToday's Pareto frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/mercury-2-5/minimax-m3-1-flash · Markdown: /api/v1/compare/mercury-2-5/minimax-m3-1-flash?format=md · llms.txt · agent skill