GPT-5.2 (xhigh) vs Qwen3.5 397B A17B (Reasoning)
For product management work, compared on the PM Index.
- GPT-5.2 (xhigh) leads on the PM Index (52.8 vs 46.8).
- Qwen3.5 397B A17B (Reasoning) is cheaper ($1.35 vs $4.81 per 1M tokens).
- GPT-5.2 (xhigh) is faster (78 vs 50 tok/s).
| Metric | GPT-5.2 (xhigh) | Qwen3.5 397B A17B (Reasoning) |
|---|---|---|
| PM Index | 52.8 | 46.8 |
| AA Intelligence | 51.3 | 45.0 |
| AA Coding | 48.7 | 41.3 |
| AA Agentic | 60.2 | 55.8 |
| Blended $/1M | $4.81 | $1.35 |
| Output tok/s | 78 | 50 |