Kimi K2.7 Code vs Step 5 Preview
Which is better for the money: Kimi K2.7 Code by Kimi or Step 5 Preview by StepFun? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Step 5 Preview scores 17.9 points higher (43.7 vs 25.8) but costs 1.2× as much to run the benchmark ($1190 vs $993; both premium class). Pick Step 5 Preview when the extra intelligence is worth the premium, otherwise Kimi K2.7 Code.
| Metric | Kimi K2.7 Code | Step 5 Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.8 | 43.7 | +69.4% Step 5 Preview is 69.4% more intelligent |
| Total AA cost (lower is better) | $992.88 | $1,190.26 | +19.9% Step 5 Preview is 19.9% more expensive |
| End-to-end time (lower is better) | 46.45s | 12.01s | −74.1% Step 5 Preview is 74.1% faster |
| Price per 1M tokens (in / out) | $0.95 / $4.00 | $1.00 / $2.70 | |
| Input modalities | Text, Image, Video | Text, Image |
Step 5 Preview vs Kimi K2.7 Code: 69.4% more intelligence, 19.9% more cost to run the AA benchmark, and 74.1% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Kimi K2.7 Code is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
- Step 5 Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Kimi K2.7 CodeStep 5 PreviewToday'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/kimi-k2-7-code/step-5 · Markdown: /api/v1/compare/kimi-k2-7-code/step-5?format=md · llms.txt · agent skill