Kimi K2.7 Code vs MiMo-V2.5-Pro
Which is better for the money: Kimi K2.7 Code by Kimi or MiMo-V2.5-Pro by Xiaomi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-17.
Trade-off
Verdict
Depends on your budget
Kimi K2.7 Code scores 0.1 points higher (43.0 vs 42.9) but costs 5.5× as much to run the benchmark ($545 vs $98.9; premium vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 42.9, and MiMo-V2.5-Pro when 42.9 is enough.
| Metric | Kimi K2.7 Code | MiMo-V2.5-Pro | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.0 | 42.9 | −0.2% MiMo-V2.5-Pro is 0.2% less intelligent |
| Total AA cost (lower is better) | $544.58 | $98.86 | −81.8% MiMo-V2.5-Pro is 81.8% cheaper |
| End-to-end time (lower is better) | 73.20s | 48.34s | −34.0% MiMo-V2.5-Pro is 34.0% faster |
| Price per 1M tokens (in / out) | $0.95 / $4.00 | $0.43 / $0.87 | |
| Input modalities | Not reported | Not reported |
MiMo-V2.5-Pro vs Kimi K2.7 Code: 0.2% less intelligence, 81.8% less cost to run the AA benchmark, and 34.0% 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, Gemini 3.7 Flash (high) scores 56.00 for $485.
- MiMo-V2.5-Pro is off the frontier: at the same or lower cost, GPT-5.6 Luna (xhigh) scores 50.10 for $95.1.
Kimi K2.7 CodeMiMo-V2.5-ProToday'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/mimo-v2-5-pro · Markdown: /api/v1/compare/kimi-k2-7-code/mimo-v2-5-pro?format=md · llms.txt · agent skill