GPT-5.1 (high) vs Qwen3.5 397B A17B (Reasoning)
For product management work, compared on the PM Index.
- GPT-5.1 (high) leads on the PM Index (48.1 vs 46.8).
- Qwen3.5 397B A17B (Reasoning) is cheaper ($1.35 vs $3.44 per 1M tokens).
- GPT-5.1 (high) is faster (139 vs 50 tok/s).
| Metric | GPT-5.1 (high) | Qwen3.5 397B A17B (Reasoning) |
|---|---|---|
| PM Index | 48.1 | 46.8 |
| AA Intelligence | 47.7 | 45.0 |
| AA Coding | 44.7 | 41.3 |
| AA Agentic | 51.3 | 55.8 |
| Blended $/1M | $3.44 | $1.35 |
| Output tok/s | 139 | 50 |