GPT-5.2 (xhigh) vs Mistral Large 3
For product management work, compared on the PM Index.
- GPT-5.2 (xhigh) leads on the PM Index (52.8 vs 22.6).
- Mistral Large 3 is cheaper ($0.75 vs $4.81 per 1M tokens).
- GPT-5.2 (xhigh) is faster (78 vs 56 tok/s).
| Metric | GPT-5.2 (xhigh) | Mistral Large 3 |
|---|---|---|
| PM Index | 52.8 | 22.6 |
| AA Intelligence | 51.3 | 22.8 |
| AA Coding | 48.7 | 22.7 |
| AA Agentic | 60.2 | 21.7 |
| Blended $/1M | $4.81 | $0.75 |
| Output tok/s | 78 | 56 |