DeepSeek R1 (Jan '25) vs Qwen3 235B A22B 2507 (Reasoning)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or Qwen3 235B A22B 2507 (Reasoning) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Clear winner
Verdict
Pick Qwen3 235B A22B 2507 (Reasoning)
Qwen3 235B A22B 2507 (Reasoning) vs DeepSeek R1 (Jan '25): 11.4% more intelligence, 49.3% less cost to run the AA benchmark, and 23.3% slower end-to-end.
| Metric | DeepSeek R1 (Jan '25) | Qwen3 235B A22B 2507 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 12.7 | +11.4% Qwen3 235B A22B 2507 … is 11.4% more intelligent |
| Total AA cost (lower is better) | $460.74 | $233.56 | −49.3% Qwen3 235B A22B 2507 … is 49.3% cheaper |
| End-to-end time (lower is better) | 18.43s | 22.73s | +23.3% Qwen3 235B A22B 2507 … is 23.3% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $0.23 / $2.30 | |
| Input modalities | Text | Text |
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 235B A22B 2507 (Reasoning) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
DeepSeek R1 (Jan '25)Qwen3 235B A22B 2507 (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/qwen3-235b-a22b-instruct-2507-reasoning · Markdown: /api/v1/compare/deepseek-r1-0120/qwen3-235b-a22b-instruct-2507-reasoning?format=md · llms.txt · agent skill