DeepSeek V4 Flash 0731 (Max) vs Kimi K3 (Max)
Which is better for the money: DeepSeek V4 Flash 0731 (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 9.3 points higher (43.6 vs 34.3) but costs 18× as much to run the benchmark ($3658 vs $200; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K3 (Max) when you need intelligence above 34.3, and DeepSeek V4 Flash 0731 (Max) when 34.3 is enough.
| Metric | DeepSeek V4 Flash 0731 (Max) | Kimi K3 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.3 | 43.6 | +27.1% Kimi K3 (Max) is 27.1% more intelligent |
| Total AA cost (lower is better) | $199.63 | $3,658.07 | +1732.4% Kimi K3 (Max) is 18× more expensive |
| End-to-end time (lower is better) | 17.94s | 56.93s | +217.3% Kimi K3 (Max) is 217.3% slower |
| Price per 1M tokens (in / out) | $0.14 / $0.28 | $3.00 / $15.0 | |
| Input modalities | Text | Text, Image |
Kimi K3 (Max) vs DeepSeek V4 Flash 0731 (Max): 27.1% more intelligence, 1732.4% more cost to run the AA benchmark, and 217.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Flash 0731 (Max) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
- Kimi K3 (Max) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
DeepSeek V4 Flash 0731 (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-flash/kimi-k3 · Markdown: /api/v1/compare/deepseek-v4-flash/kimi-k3?format=md · llms.txt · agent skill