GPT-5.2 vs Qwen3.6 Max Preview
For product management work, compared on the PM Index.
- Qwen3.6 Max Preview leads on the PM Index (53.7 vs 52.8).
- Qwen3.6 Max Preview is cheaper ($2.92 vs $4.81 per 1M tokens).
- GPT-5.2 is faster (78 vs 46 tok/s).
| Metric | GPT-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| PM Index | 52.8 | 53.7 |
| AA Intelligence | 51.3 | 51.8 |
| AA Coding | 48.7 | 44.9 |
| AA Agentic | 60.2 | 64.8 |
| Blended $/1M | $4.81 | $2.92 |
| Output tok/s | 78 | 46 |