DeepSeek R1 (Jan '25) vs Qwen3.8 Max
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or Qwen3.8 Max by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
Qwen3.8 Max scores 28.8 points higher (40.2 vs 11.4) but costs 6.9× as much to run the benchmark ($3172 vs $461; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Qwen3.8 Max when you need intelligence above 11.4, and DeepSeek R1 (Jan '25) when 11.4 is enough.
| Metric | DeepSeek R1 (Jan '25) | Qwen3.8 Max | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 40.2 | +252.6% Qwen3.8 Max is 3.5× more intelligent |
| Total AA cost (lower is better) | $460.74 | $3,172.37 | +588.5% Qwen3.8 Max is 6.9× more expensive |
| End-to-end time (lower is better) | 19.94s | 64.42s | +223.1% Qwen3.8 Max is 223.1% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $2.00 / $6.00 | |
| Input modalities | Text | Text, Image, Video |
Qwen3.8 Max vs DeepSeek R1 (Jan '25): 252.6% more intelligence, 588.5% more cost to run the AA benchmark, and 223.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek R1 (Jan '25) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- Qwen3.8 Max is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
DeepSeek R1 (Jan '25)Qwen3.8 MaxToday'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-r1-0120/qwen3-8-max-0803 · Markdown: /api/v1/compare/deepseek-r1-0120/qwen3-8-max-0803?format=md · llms.txt · agent skill