Kimi K2.7 Code vs MiMo-V2.5
Which is better for the money: Kimi K2.7 Code by Kimi or MiMo-V2.5 by Xiaomi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-07.
Trade-off
Verdict
Depends on your budget
Kimi K2.7 Code scores 5.0 points higher (43.0 vs 38.0) but costs 22× as much to run the benchmark ($545 vs $25.2; premium vs budget cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 38.0, and MiMo-V2.5 when 38.0 is enough.
| Metric | Kimi K2.7 Code | MiMo-V2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.0 | 38.0 | −11.6% MiMo-V2.5 is 11.6% less intelligent |
| Total AA cost (lower is better) | $544.58 | $25.18 | −95.4% MiMo-V2.5 is 95.4% cheaper |
| End-to-end time (lower is better) | 66.82s | 28.60s | −57.2% MiMo-V2.5 is 57.2% faster |
| Price per 1M tokens (in / out) | $0.95 / $4.00 | $0.14 / $0.28 | |
| Input modalities | Not reported | Not reported |
MiMo-V2.5 vs Kimi K2.7 Code: 11.6% less intelligence, 95.4% less cost to run the AA benchmark, and 57.2% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Kimi K2.7 Code is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
- MiMo-V2.5 is off the frontier: at the same or lower cost, GPT-5.6 Luna (medium) scores 38.90 for $21.1.
Kimi K2.7 CodeMiMo-V2.5Today'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/kimi-k2-7-code/mimo-v2-5-0424 · Markdown: /api/v1/compare/kimi-k2-7-code/mimo-v2-5-0424?format=md · llms.txt · agent skill