DeepSeek V4 Pro 0813 (Max) vs Kimi K3 (Max)
Which is better for the money: DeepSeek V4 Pro 0813 (Max) by DeepSeek or Kimi K3 (Max) by Kimi? 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
Kimi K3 (Max) scores 7.6 points higher (43.6 vs 36.0) but costs 3.3× as much to run the benchmark ($3658 vs $1122; flagship vs premium cost classes). They are not alternatives at one budget: pick Kimi K3 (Max) when you need intelligence above 36.0, and DeepSeek V4 Pro 0813 (Max) when 36.0 is enough.
| Metric | DeepSeek V4 Pro 0813 (Max) | Kimi K3 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 36.0 | 43.6 | +21.1% Kimi K3 (Max) is 21.1% more intelligent |
| Total AA cost (lower is better) | $1,122.27 | $3,658.07 | +226.0% Kimi K3 (Max) is 3.3× more expensive |
| End-to-end time (lower is better) | 25.87s | 58.57s | +126.4% Kimi K3 (Max) is 126.4% slower |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $3.00 / $15.0 | |
| Input modalities | Text | Text, Image |
Kimi K3 (Max) vs DeepSeek V4 Pro 0813 (Max): 21.1% more intelligence, 226.0% more cost to run the AA benchmark, and 126.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro 0813 (Max) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- Kimi K3 (Max) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
DeepSeek V4 Pro 0813 (Max)Kimi K3 (Max)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-v4-pro/kimi-k3 · Markdown: /api/v1/compare/deepseek-v4-pro/kimi-k3?format=md · llms.txt · agent skill