DeepSeek V3.2 Exp (Non-reasoning) vs Qwen3.5 397B A17B (Reasoning)
For product management work, compared on the PM Index.
- Qwen3.5 397B A17B (Reasoning) leads on the PM Index (46.8 vs 29.1).
- DeepSeek V3.2 Exp (Non-reasoning) is cheaper ($0.31 vs $1.35 per 1M tokens).
| Metric | DeepSeek V3.2 Exp (Non-reasoning) | Qwen3.5 397B A17B (Reasoning) |
|---|---|---|
| PM Index | 29.1 | 46.8 |
| AA Intelligence | 28.4 | 45.0 |
| AA Coding | 30.0 | 41.3 |
| AA Agentic | 31.0 | 55.8 |
| Blended $/1M | $0.31 | $1.35 |
| Output tok/s | — | 50 |