Claude Sonnet 4.6 (Non-reasoning, High Effort) vs GPT-5.1 (high)
For product management work, compared on the PM Index.
- GPT-5.1 (high) leads on the PM Index (48.1 vs 48.0).
- GPT-5.1 (high) is cheaper ($3.44 vs $6.00 per 1M tokens).
- GPT-5.1 (high) is faster (139 vs 43 tok/s).
| Metric | Claude Sonnet 4.6 (Non-reasoning, High Effort) | GPT-5.1 (high) |
|---|---|---|
| PM Index | 48.0 | 48.1 |
| AA Intelligence | 44.4 | 47.7 |
| AA Coding | 46.4 | 44.7 |
| AA Agentic | 61.6 | 51.3 |
| Blended $/1M | $6.00 | $3.44 |
| Output tok/s | 43 | 139 |