Grok 4.3 (Non-reasoning) vs Kimi K2.7 Code
Which is better for the money: Grok 4.3 (Non-reasoning) by SpaceXAI or Kimi K2.7 Code by Kimi? 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 11.8 points higher (26.3 vs 14.5) but costs 4.9× as much to run the benchmark ($993 vs $203; premium vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 14.5, and Grok 4.3 (Non-reasoning) when 14.5 is enough.
| Metric | Grok 4.3 (Non-reasoning) | Kimi K2.7 Code | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 14.5 | 26.3 | +81.4% Kimi K2.7 Code is 81.4% more intelligent |
| Total AA cost (lower is better) | $203.06 | $992.88 | +389.0% Kimi K2.7 Code is 4.9× more expensive |
| End-to-end time (lower is better) | 4.49s | 41.22s | +818.0% Kimi K2.7 Code is 818.0% slower |
| Price per 1M tokens (in / out) | $1.25 / $2.50 | $0.95 / $4.00 | |
| Input modalities | Not reported | Not reported |
Kimi K2.7 Code vs Grok 4.3 (Non-reasoning): 81.4% more intelligence, 389.0% more cost to run the AA benchmark, and 818.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Grok 4.3 (Non-reasoning) is off the frontier: at the same or lower cost, GPT-5.6 Luna (xhigh) scores 34.80 for $179.
- Kimi K2.7 Code is off the frontier: at the same or lower cost, GLM-5.3-Flash scores 41.90 for $280.
Grok 4.3 (Non-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/grok-4-3-non-reasoning/kimi-k2-7-code · Markdown: /api/v1/compare/grok-4-3-non-reasoning/kimi-k2-7-code?format=md · llms.txt · agent skill