DeepSeek V3 (Dec '24) vs Kimi K3 (Low)
Which is better for the money: DeepSeek V3 (Dec '24) by DeepSeek or Kimi K3 (Low) by Kimi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Kimi K3 (Low) scores 21.6 points higher (30.1 vs 8.5) but costs 47× as much to run the benchmark ($1190 vs $25.4; premium vs budget cost classes). They are not alternatives at one budget: pick Kimi K3 (Low) when you need intelligence above 8.5, and DeepSeek V3 (Dec '24) when 8.5 is enough.
| Metric | DeepSeek V3 (Dec '24) | Kimi K3 (Low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 30.1 | +254.1% Kimi K3 (Low) is 3.5× more intelligent |
| Total AA cost (lower is better) | $25.37 | $1,190.42 | +4592.2% Kimi K3 (Low) is 47× more expensive |
| End-to-end time (lower is better) | 11.89s | 66.33s | +457.9% Kimi K3 (Low) is 457.9% slower |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $3.00 / $15.0 | |
| Input modalities | Text | Text, Image |
Kimi K3 (Low) vs DeepSeek V3 (Dec '24): 254.1% more intelligence, 4592.2% more cost to run the AA benchmark, and 457.9% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V3 (Dec '24) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Kimi K3 (Low) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
DeepSeek V3 (Dec '24)Kimi K3 (Low)Today'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/deepseek-v3/kimi-k3-low · Markdown: /api/v1/compare/deepseek-v3/kimi-k3-low?format=md · llms.txt · agent skill