Kimi K2.7 Code vs Mistral Large 3
Which is better for the money: Kimi K2.7 Code by Kimi or Mistral Large 3 by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-09-01.
Trade-off
Verdict
Depends on your budget
Kimi K2.7 Code scores 27.1 points higher (43.0 vs 15.9) but costs 7.7× as much to run the benchmark ($545 vs $71.1; premium vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 15.9, and Mistral Large 3 when 15.9 is enough.
| Metric | Kimi K2.7 Code | Mistral Large 3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.0 | 15.9 | −63.0% Mistral Large 3 is 63.0% less intelligent |
| Total AA cost (lower is better) | $544.58 | $71.14 | −86.9% Mistral Large 3 is 86.9% cheaper |
| End-to-end time (lower is better) | 60.38s | 7.48s | −87.6% Mistral Large 3 is 87.6% faster |
| Price per 1M tokens (in / out) | $0.95 / $4.00 | $0.50 / $1.50 | |
| Input modalities | Not reported | Not reported |
Mistral Large 3 vs Kimi K2.7 Code: 63.0% less intelligence, 86.9% less cost to run the AA benchmark, and 87.6% 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 57.50 for $138.
- Mistral Large 3 is off the frontier: at the same or lower cost, Agnes 2.5 Pro Beta scores 49.10 for $55.6.
Kimi K2.7 CodeMistral Large 3Today'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-large-3 · Markdown: /api/v1/compare/kimi-k2-7-code/mistral-large-3?format=md · llms.txt · agent skill