Mercury 2 vs MiniMax-M3
Which is better for the money: Mercury 2 by Inception or MiniMax-M3 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 scores 18.4 points higher (29.2 vs 10.8) but costs 5.1× as much to run the benchmark ($538 vs $105; premium vs mid-range cost classes). They are not alternatives at one budget: pick MiniMax-M3 when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | Mercury 2 | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 10.8 | 29.2 | +170.4% MiniMax-M3 is 2.7× more intelligent |
| Total AA cost (lower is better) | $104.94 | $537.98 | +412.7% MiniMax-M3 is 5.1× more expensive |
| End-to-end time (lower is better) | 6.65s | 25.47s | +283.0% MiniMax-M3 is 283.0% slower |
| Price per 1M tokens (in / out) | $0.25 / $0.75 | $0.30 / $1.20 | |
| Input modalities | Text | Text, Image, Video |
MiniMax-M3 vs Mercury 2: 170.4% more intelligence, 412.7% more cost to run the AA benchmark, and 283.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
Mercury 2MiniMax-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/mercury-2/minimax-m3 · Markdown: /api/v1/compare/mercury-2/minimax-m3?format=md · llms.txt · agent skill