Kimi K2.7 Code vs Mistral Small 3.2
Which is better for the money: Kimi K2.7 Code by Kimi or Mistral Small 3.2 by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-19.
Trade-off
Verdict
Depends on your budget
Kimi K2.7 Code scores 32.3 points higher (43.0 vs 10.7) but costs 4.2× as much to run the benchmark ($545 vs $129; premium vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 10.7, and Mistral Small 3.2 when 10.7 is enough.
| Metric | Kimi K2.7 Code | Mistral Small 3.2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.0 | 10.7 | −75.1% Mistral Small 3.2 is 75.1% less intelligent |
| Total AA cost (lower is better) | $544.58 | $128.79 | −76.4% Mistral Small 3.2 is 76.4% cheaper |
| End-to-end time (lower is better) | 75.91s | 4.18s | −94.5% Mistral Small 3.2 is 94.5% faster |
| Price per 1M tokens (in / out) | $0.95 / $4.00 | $0.10 / $0.30 | |
| Input modalities | Not reported | Not reported |
Mistral Small 3.2 vs Kimi K2.7 Code: 75.1% less intelligence, 76.4% less cost to run the AA benchmark, and 94.5% 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.
- Mistral Small 3.2 is off the frontier: at the same or lower cost, GPT-5.6 Luna (xhigh) scores 50.10 for $95.1.
Kimi K2.7 CodeMistral Small 3.2Today'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/mistral-small-3-2 · Markdown: /api/v1/compare/kimi-k2-7-code/mistral-small-3-2?format=md · llms.txt · agent skill