DeepSeek V3.2 Exp (Non-reasoning) vs Gemini 2.5 Pro
For product management work, compared on the PM Index.
- Gemini 2.5 Pro leads on the PM Index (34.0 vs 29.1).
- DeepSeek V3.2 Exp (Non-reasoning) is cheaper ($0.31 vs $3.44 per 1M tokens).
| Metric | DeepSeek V3.2 Exp (Non-reasoning) | Gemini 2.5 Pro |
|---|---|---|
| PM Index | 29.1 | 34.0 |
| AA Intelligence | 28.4 | 34.6 |
| AA Coding | 30.0 | 32.0 |
| AA Agentic | 31.0 | 32.7 |
| Blended $/1M | $0.31 | $3.44 |
| Output tok/s | — | 141 |