DeepSeek R1 (Jan '25) vs Qwen3.5 122B A10B (Reasoning)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or Qwen3.5 122B A10B (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 122B A10B (Reasoning) scores 4.2 points higher (15.6 vs 11.4) but costs 1.4× as much to run the benchmark ($661 vs $461; premium vs mid-range cost classes). Pick Qwen3.5 122B A10B (Reasoning) when the extra intelligence is worth the premium, otherwise DeepSeek R1 (Jan '25).
| Metric | DeepSeek R1 (Jan '25) | Qwen3.5 122B A10B (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 15.6 | +36.8% Qwen3.5 122B A10B (Re… is 36.8% more intelligent |
| Total AA cost (lower is better) | $460.74 | $661.29 | +43.5% Qwen3.5 122B A10B (Re… is 43.5% more expensive |
| End-to-end time (lower is better) | 18.69s | 21.37s | +14.3% Qwen3.5 122B A10B (Re… is 14.3% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $0.40 / $3.20 | |
| Input modalities | Text | Text, Image |
Qwen3.5 122B A10B (Reasoning) vs DeepSeek R1 (Jan '25): 36.8% more intelligence, 43.5% more cost to run the AA benchmark, and 14.3% 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 122B A10B (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
DeepSeek R1 (Jan '25)Qwen3.5 122B A10B (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/qwen3-5-122b-a10b · Markdown: /api/v1/compare/deepseek-r1-0120/qwen3-5-122b-a10b?format=md · llms.txt · agent skill