DeepSeek R1 Distill Qwen 32B — Benchmarks
Benchmark scores for DeepSeek R1 Distill Qwen 32B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Coding
| Benchmark | Score | Rank |
|---|---|---|
| LiveBench Coding | 33.7 | #10 / 13 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| LiveBench Math | 59.4 | #4 / 13 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| LiveBench Reasoning | 52.3 | #6 / 13 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.