Kimi K2.5 (Reasoning) vs Kimi K2.7 Code
Which is better for the money: Kimi K2.5 (Reasoning) by Kimi or Kimi K2.7 Code by Kimi? 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 7.0 points higher (43.0 vs 36.0) but costs 1.8× as much to run the benchmark ($545 vs $304; premium vs mid-range cost classes). Pick Kimi K2.7 Code when the extra intelligence is worth the premium, otherwise Kimi K2.5 (Reasoning).
| Metric | Kimi K2.5 (Reasoning) | Kimi K2.7 Code | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 36.0 | 43.0 | +19.4% Kimi K2.7 Code is 19.4% more intelligent |
| Total AA cost (lower is better) | $304.21 | $544.58 | +79.0% Kimi K2.7 Code is 79.0% more expensive |
| End-to-end time (lower is better) | 83.37s | 75.91s | −8.9% Kimi K2.7 Code is 8.9% faster |
| Price per 1M tokens (in / out) | $0.60 / $3.00 | $0.95 / $4.00 | |
| Input modalities | Not reported | Not reported |
Kimi K2.7 Code vs Kimi K2.5 (Reasoning): 19.4% more intelligence, 79.0% more cost to run the AA benchmark, and 8.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Kimi K2.5 (Reasoning) is off the frontier: at the same or lower cost, Gemini 3.7 Flash (medium) scores 53.40 for $278.
- Kimi K2.7 Code is off the frontier: at the same or lower cost, Gemini 3.7 Flash (high) scores 56.00 for $485.
Kimi K2.5 (Reasoning)Kimi K2.7 CodeToday'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-k2-5/kimi-k2-7-code · Markdown: /api/v1/compare/kimi-k2-5/kimi-k2-7-code?format=md · llms.txt · agent skill