Gemini 3.1 Pro Preview vs Kimi K2.7 Code
Which is better for the money: Gemini 3.1 Pro Preview by Google or Kimi K2.7 Code by Kimi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-07.
Trade-off
Verdict
Depends on your budget
Gemini 3.1 Pro Preview scores 4.7 points higher (47.7 vs 43.0) but costs 1.5× as much to run the benchmark ($812 vs $545; both premium class). Pick Gemini 3.1 Pro Preview when the extra intelligence is worth the premium, otherwise Kimi K2.7 Code.
| Metric | Gemini 3.1 Pro Preview | Kimi K2.7 Code | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 47.7 | 43.0 | −9.9% Kimi K2.7 Code is 9.9% less intelligent |
| Total AA cost (lower is better) | $811.90 | $544.58 | −32.9% Kimi K2.7 Code is 32.9% cheaper |
| End-to-end time (lower is better) | 34.11s | 66.82s | +95.9% Kimi K2.7 Code is 95.9% slower |
| Price per 1M tokens (in / out) | $2.00 / $12.0 | $0.95 / $4.00 | |
| Input modalities | Not reported | Not reported |
Kimi K2.7 Code vs Gemini 3.1 Pro Preview: 9.9% less intelligence, 32.9% less cost to run the AA benchmark, and 95.9% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 3.1 Pro Preview is off the frontier: at the same or lower cost, Muse Spark 1.2 (xhigh) scores 56.80 for $639.
- Kimi K2.7 Code is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
Gemini 3.1 Pro PreviewKimi K2.7 CodeToday'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/gemini-3-1-pro-preview/kimi-k2-7-code · Markdown: /api/v1/compare/gemini-3-1-pro-preview/kimi-k2-7-code?format=md · llms.txt · agent skill