Kimi K2.7 Code vs Kimi K3 (low)
Which is better for the money: Kimi K2.7 Code by Kimi or Kimi K3 (low) by Kimi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-07.
Clear winner
Verdict
Pick Kimi K3 (low)
Kimi K3 (low) vs Kimi K2.7 Code: 12.3% more intelligence, 48.1% less cost to run the AA benchmark, and 0.4% faster end-to-end.
| Metric | Kimi K2.7 Code | Kimi K3 (low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.0 | 48.3 | +12.3% Kimi K3 (low) is 12.3% more intelligent |
| Total AA cost (lower is better) | $544.58 | $282.64 | −48.1% Kimi K3 (low) is 48.1% cheaper |
| End-to-end time (lower is better) | 66.82s | 66.53s | −0.4% Kimi K3 (low) is 0.4% faster |
| Price per 1M tokens (in / out) | $0.95 / $4.00 | $3.00 / $15.0 | |
| Input modalities | Not reported | Not reported |
Today's Pareto frontier
Against the frontier
- Kimi K2.7 Code is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
- Kimi K3 (low) is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
Kimi K2.7 CodeKimi K3 (low)Today's Pareto 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/kimi-k3-low · Markdown: /api/v1/compare/kimi-k2-7-code/kimi-k3-low?format=md · llms.txt · agent skill