Celeris-1 vs Kimi K2.7 Code
Which is better for the money: Celeris-1 by Celeris or Kimi K2.7 Code by Kimi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-09-30.
Trade-off
Verdict
Depends on your budget
Kimi K2.7 Code scores 19.5 points higher (25.8 vs 6.3) but costs 17× as much to run the benchmark ($993 vs $60.0; premium vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K2.7 Code when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | Kimi K2.7 Code | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 25.8 | +309.5% Kimi K2.7 Code is 4.1× more intelligent |
| Total AA cost (lower is better) | $59.99 | $992.88 | +1555.1% Kimi K2.7 Code is 17× more expensive |
| End-to-end time (lower is better) | 0.90s | 39.06s | +4240.0% Kimi K2.7 Code is 4240.0% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.95 / $4.00 | |
| Input modalities | Text, Image | Text, Image, Video |
Kimi K2.7 Code vs Celeris-1: 309.5% more intelligence, 1555.1% more cost to run the AA benchmark, and 4240.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Celeris-1 is off the frontier: at the same or lower cost, GPT-6 Luna (high) scores 32.10 for $47.9.
- Kimi K2.7 Code is off the frontier: at the same or lower cost, GPT-6.1 Sol (xhigh) scores 51.00 for $662.
Celeris-1Kimi 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/celeris-1/kimi-k2-7-code · Markdown: /api/v1/compare/celeris-1/kimi-k2-7-code?format=md · llms.txt · agent skill