DeepSeek R1 (Jan '25) vs Qwen3.5 397B A17B (Reasoning)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or Qwen3.5 397B A17B (Reasoning) 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
Qwen3.5 397B A17B (Reasoning) scores 7.0 points higher (18.4 vs 11.4) but costs 2.0× as much to run the benchmark ($941 vs $461; premium vs mid-range cost classes). Pick Qwen3.5 397B A17B (Reasoning) when the extra intelligence is worth the premium, otherwise DeepSeek R1 (Jan '25).
| Metric | DeepSeek R1 (Jan '25) | Qwen3.5 397B A17B (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 18.4 | +61.4% Qwen3.5 397B A17B (Re… is 61.4% more intelligent |
| Total AA cost (lower is better) | $460.74 | $940.97 | +104.2% Qwen3.5 397B A17B (Re… is 2.0× more expensive |
| End-to-end time (lower is better) | 18.69s | 65.86s | +252.4% Qwen3.5 397B A17B (Re… is 252.4% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $0.60 / $3.60 | |
| Input modalities | Text | Text, Image |
Qwen3.5 397B A17B (Reasoning) vs DeepSeek R1 (Jan '25): 61.4% more intelligence, 104.2% more cost to run the AA benchmark, and 252.4% 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.
- Qwen3.5 397B A17B (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
DeepSeek R1 (Jan '25)Qwen3.5 397B A17B (Reasoning)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-r1-0120/qwen3-5-397b-a17b · Markdown: /api/v1/compare/deepseek-r1-0120/qwen3-5-397b-a17b?format=md · llms.txt · agent skill