DeepSeek V4 Pro 0813 (Non-reasoning) vs Qwen3.8 Max (0902)
Which is better for the money: DeepSeek V4 Pro 0813 (Non-reasoning) by DeepSeek or Qwen3.8 Max (0902) by Alibaba? 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
Qwen3.8 Max (0902) scores 25.0 points higher (45.4 vs 20.4) but costs 11× as much to run the benchmark ($4935 vs $451; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Qwen3.8 Max (0902) 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) | Qwen3.8 Max (0902) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.4 | 45.4 | +122.5% Qwen3.8 Max (0902) is 2.2× more intelligent |
| Total AA cost (lower is better) | $450.76 | $4,934.79 | +994.8% Qwen3.8 Max (0902) is 11× more expensive |
| End-to-end time (lower is better) | 6.74s | 62.92s | +833.5% Qwen3.8 Max (0902) is 833.5% slower |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $2.00 / $6.00 | |
| Input modalities | Text | Text, Image |
Qwen3.8 Max (0902) vs DeepSeek V4 Pro 0813 (Non-reasoning): 122.5% more intelligence, 994.8% more cost to run the AA benchmark, and 833.5% 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.
- Qwen3.8 Max (0902) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
DeepSeek V4 Pro 0813 (Non-reasoning)Qwen3.8 Max (0902)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/qwen3-8-max · Markdown: /api/v1/compare/deepseek-v4-pro-non-reasoning/qwen3-8-max?format=md · llms.txt · agent skill