Kimi K2.7 Code vs MiniMax-M2.7
Which is better for the money: Kimi K2.7 Code by Kimi or MiniMax-M2.7 by MiniMax? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-09-09.
Trade-off
Verdict
Depends on your budget
Kimi K2.7 Code scores 3.1 points higher (26.3 vs 23.2) but costs 4.2× as much to run the benchmark ($993 vs $236; premium vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 23.2, and MiniMax-M2.7 when 23.2 is enough.
| Metric | Kimi K2.7 Code | MiniMax-M2.7 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 26.3 | 23.2 | −11.8% MiniMax-M2.7 is 11.8% less intelligent |
| Total AA cost (lower is better) | $992.88 | $235.96 | −76.2% MiniMax-M2.7 is 76.2% cheaper |
| End-to-end time (lower is better) | 41.22s | 42.23s | +2.5% MiniMax-M2.7 is 2.5% slower |
| Price per 1M tokens (in / out) | $0.95 / $4.00 | $0.30 / $1.20 | |
| Input modalities | Not reported | Not reported |
MiniMax-M2.7 vs Kimi K2.7 Code: 11.8% less intelligence, 76.2% less cost to run the AA benchmark, and 2.5% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Kimi K2.7 Code is off the frontier: at the same or lower cost, GLM-5.3-Flash scores 41.90 for $280.
- MiniMax-M2.7 is off the frontier: at the same or lower cost, GPT-5.6 Luna (xhigh) scores 34.80 for $179.
Kimi K2.7 CodeMiniMax-M2.7Today'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/kimi-k2-7-code/minimax-m2-7 · Markdown: /api/v1/compare/kimi-k2-7-code/minimax-m2-7?format=md · llms.txt · agent skill