Gemma 4 31B (Non-reasoning) vs Kimi K2.7 Code
Which is better for the money: Gemma 4 31B (Non-reasoning) by Google 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 20.7 points higher (43.0 vs 22.3) but costs 16× as much to run the benchmark ($545 vs $33.8; premium vs budget cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 22.3, and Gemma 4 31B (Non-reasoning) when 22.3 is enough.
| Metric | Gemma 4 31B (Non-reasoning) | Kimi K2.7 Code | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 22.3 | 43.0 | +92.8% Kimi K2.7 Code is 92.8% more intelligent |
| Total AA cost (lower is better) | $33.84 | $544.58 | +1509.3% Kimi K2.7 Code is 16× more expensive |
| End-to-end time (lower is better) | 7.47s | 75.91s | +916.2% Kimi K2.7 Code is 916.2% slower |
| Price per 1M tokens (in / out) | $0.15 / $0.40 | $0.95 / $4.00 | |
| Input modalities | Not reported | Not reported |
Kimi K2.7 Code vs Gemma 4 31B (Non-reasoning): 92.8% more intelligence, 1509.3% more cost to run the AA benchmark, and 916.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Gemma 4 31B (Non-reasoning) is off the frontier: at the same or lower cost, GPT-5.6 Luna (medium) scores 38.90 for $21.1.
- Kimi K2.7 Code is off the frontier: at the same or lower cost, Gemini 3.7 Flash (high) scores 56.00 for $485.
Gemma 4 31B (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/gemma-4-31b-non-reasoning/kimi-k2-7-code · Markdown: /api/v1/compare/gemma-4-31b-non-reasoning/kimi-k2-7-code?format=md · llms.txt · agent skill