DeepSeek R1 0528 vs DeepSeek V3.2-Exp
| Spec | DeepSeek R1 0528 | DeepSeek V3.2-Exp |
|---|---|---|
| Respan Index | 21.0 (#111) | 22.0 (#109) |
| Blended price per 1M | $0.912 | $0.305 |
| Context window | - | 128K |
| Input / output per 1M | $0.5 / $2.15 | $0.27 / $0.41 |
| Max output | 66K | - |
| Input | text | text |
| Released | 2025-05-28 | 2025-09-29 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | DeepSeek R1 0528 | DeepSeek V3.2-Exp |
|---|---|---|
| Coding | 5.3 DeepSeek R1 0528 | 5.2 DeepSeek V3.2-Exp |
| Agents | 18.9* DeepSeek R1 0528 | 22.5 DeepSeek V3.2-Exp |
| Reasoning | 23.1 DeepSeek R1 0528 | 24.2 DeepSeek V3.2-Exp |
| Knowledge & language | 19.6 DeepSeek R1 0528 | 19.6 DeepSeek V3.2-Exp |
| Human preference | 48.0 DeepSeek R1 0528 | 47.2 DeepSeek V3.2-Exp |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
DeepSeek V3.2-Exp leads on 4 of the 6 benchmarks both report. Higher is better. Each score links to where it was published.
FAQ
Is DeepSeek R1 0528 better than DeepSeek V3.2-Exp?
DeepSeek V3.2-Exp scores 22.0 on the Respan Index (#109), ahead of DeepSeek R1 0528 at 21.0 (#111). DeepSeek V3.2-Exp leads on 4 of the 6 benchmarks both report.
Which is cheaper, DeepSeek R1 0528 or DeepSeek V3.2-Exp?
DeepSeek R1 0528 lists at $0.5 input and $2.15 output per 1M tokens; DeepSeek V3.2-Exp at $0.27 and $0.41. DeepSeek V3.2-Exp is 3.0x cheaper per token at list price.