DeepSeek V4 Pro 0813 (Non-reasoning) vs Kimi K3 (Max)
Which is better for the money: DeepSeek V4 Pro 0813 (Non-reasoning) 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 23.2 points higher (43.6 vs 20.4) but costs 8.1× as much to run the benchmark ($3658 vs $451; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K3 (Max) when you need intelligence above 20.4, and DeepSeek V4 Pro 0813 (Non-reasoning) when 20.4 is enough.
| Metric | DeepSeek V4 Pro 0813 (Non-reasoning) | Kimi K3 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.4 | 43.6 | +113.7% Kimi K3 (Max) is 2.1× more intelligent |
| Total AA cost (lower is better) | $450.76 | $3,658.07 | +711.5% Kimi K3 (Max) is 8.1× more expensive |
| End-to-end time (lower is better) | 6.84s | 58.57s | +756.3% Kimi K3 (Max) is 756.3% 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 (Non-reasoning): 113.7% more intelligence, 711.5% more cost to run the AA benchmark, and 756.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4 Pro 0813 (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- 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 (Non-reasoning)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-non-reasoning/kimi-k3 · Markdown: /api/v1/compare/deepseek-v4-pro-non-reasoning/kimi-k3?format=md · llms.txt · agent skill