Claude Opus 4.5 (Non-reasoning) vs GPT-5.2 (xhigh)
For product management work, compared on the PM Index.
- GPT-5.2 (xhigh) leads on the PM Index (52.8 vs 46.3).
- GPT-5.2 (xhigh) is cheaper ($4.81 vs $10.00 per 1M tokens).
- GPT-5.2 (xhigh) is faster (78 vs 46 tok/s).
| Metric | Claude Opus 4.5 (Non-reasoning) | GPT-5.2 (xhigh) |
|---|---|---|
| PM Index | 46.3 | 52.8 |
| AA Intelligence | 43.1 | 51.3 |
| AA Coding | 42.9 | 48.7 |
| AA Agentic | 59.2 | 60.2 |
| Blended $/1M | $10.00 | $4.81 |
| Output tok/s | 46 | 78 |