GPT-5.2 vs Qwen3.7 Max
For product management work, compared on the PM Index.
- Qwen3.7 Max leads on the PM Index (50.5 vs 46.5).
- Qwen3.7 Max is cheaper ($3.75 vs $4.81 per 1M tokens).
- Qwen3.7 Max is faster (179 vs 77 tok/s).
| Metric | GPT-5.2 | Qwen3.7 Max |
|---|---|---|
| PM Index | 46.5 | 50.5 |
| AA Intelligence | 42.2 | 46.0 |
| AA Coding | 48.7 | 50.1 |
| AA Agentic | 60.2 | 66.6 |
| Blended $/1M | $4.81 | $3.75 |
| Output tok/s | 77 | 179 |