Kimi K2.7 Code vs Mistral Small 4 (Reasoning)
Which is better for the money: Kimi K2.7 Code by Kimi or Mistral Small 4 (Reasoning) by Mistral? 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 14.8 points higher (26.3 vs 11.5) but costs 13× as much to run the benchmark ($993 vs $78.7; premium vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 11.5, and Mistral Small 4 (Reasoning) when 11.5 is enough.
| Metric | Kimi K2.7 Code | Mistral Small 4 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 26.3 | 11.5 | −56.3% Mistral Small 4 (Reas… is 56.3% less intelligent |
| Total AA cost (lower is better) | $992.88 | $78.70 | −92.1% Mistral Small 4 (Reas… is 92.1% cheaper |
| End-to-end time (lower is better) | 41.22s | 15.61s | −62.1% Mistral Small 4 (Reas… is 62.1% faster |
| Price per 1M tokens (in / out) | $0.95 / $4.00 | $0.15 / $0.60 | |
| Input modalities | Not reported | Not reported |
Mistral Small 4 (Reasoning) vs Kimi K2.7 Code: 56.3% less intelligence, 92.1% less cost to run the AA benchmark, and 62.1% 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, GLM-5.3-Flash scores 41.90 for $280.
- Mistral Small 4 (Reasoning) is off the frontier: at the same or lower cost, MiMo-V2.5 scores 22.30 for $42.6.
Kimi K2.7 CodeMistral Small 4 (Reasoning)Today'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-4 · Markdown: /api/v1/compare/kimi-k2-7-code/mistral-small-4?format=md · llms.txt · agent skill