GPT-5.4 mini (xhigh) vs Kimi K2.7 Code
Which is better for the money: GPT-5.4 mini (xhigh) by OpenAI 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.
Clear winner
Verdict
Pick Kimi K2.7 Code
Kimi K2.7 Code vs GPT-5.4 mini (xhigh): 5.1% more intelligence, 50.3% less cost to run the AA benchmark, and 407.4% slower end-to-end.
| Metric | GPT-5.4 mini (xhigh) | Kimi K2.7 Code | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 40.9 | 43.0 | +5.1% Kimi K2.7 Code is 5.1% more intelligent |
| Total AA cost (lower is better) | $1,095.81 | $544.58 | −50.3% Kimi K2.7 Code is 50.3% cheaper |
| End-to-end time (lower is better) | 14.96s | 75.91s | +407.4% Kimi K2.7 Code is 407.4% slower |
| Price per 1M tokens (in / out) | $0.75 / $4.50 | $0.95 / $4.00 | |
| Input modalities | Not reported | Not reported |
Today's Pareto frontier
Against the frontier
- GPT-5.4 mini (xhigh) is off the frontier: at the same or lower cost, Grok 4.6 (high) scores 60.90 for $1068.
- Kimi K2.7 Code is off the frontier: at the same or lower cost, Gemini 3.7 Flash (high) scores 56.00 for $485.
GPT-5.4 mini (xhigh)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/gpt-5-4-mini/kimi-k2-7-code · Markdown: /api/v1/compare/gpt-5-4-mini/kimi-k2-7-code?format=md · llms.txt · agent skill