DeepSeek R1 vs DeepSeek V3.1
| Spec | DeepSeek R1 | DeepSeek V3.1 |
|---|---|---|
| Respan Index | 18.8 (#137) | 18.9 (#136) |
| Blended price per 1M | $1.15 | $0.425 |
| Context window | 128K | 128K |
| Input / output per 1M | $0.7 / $2.5 | $0.25 / $0.95 |
| Max output | 33K | - |
| Input | text | text |
| Released | 2025-01-20 | 2025-08-21 |
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 | DeepSeek V3.1 |
|---|---|---|
| Coding | 3.6 DeepSeek R1 | 4.6 DeepSeek V3.1 |
| Agents | 16.4 DeepSeek R1 | 10.9 DeepSeek V3.1 |
| Reasoning | 21.2 DeepSeek R1 | 25.6 DeepSeek V3.1 |
| Knowledge & language | 17.5 DeepSeek R1 | 14.5* DeepSeek V3.1 |
| Human preference | 45.2 DeepSeek R1 | 47.9 DeepSeek V3.1 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
DeepSeek V3.1 leads on 4 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | DeepSeek R1 | DeepSeek V3.1 |
|---|---|---|
| LMArena Elo | 1398 | 1417 |
| WeirdML (Håvard Tveit Ihle) | 36.5% | 38.4% |
| SimpleBench (SimpleBench) | 30.9% | 40% |
| AIME 2025 | 70% | 90.8% |
FAQ
Is DeepSeek R1 better than DeepSeek V3.1?
DeepSeek V3.1 scores 18.9 on the Respan Index (#136), ahead of DeepSeek R1 at 18.8 (#137). DeepSeek V3.1 leads on 4 of the 4 benchmarks both report.
Which is cheaper, DeepSeek R1 or DeepSeek V3.1?
DeepSeek R1 lists at $0.7 input and $2.5 output per 1M tokens; DeepSeek V3.1 at $0.25 and $0.95. DeepSeek V3.1 is 2.7x cheaper per token at list price.
Which has the larger context window?
Both accept 128K tokens of context.