DeepSeek R1 — Benchmarks
Benchmark scores for DeepSeek R1 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #34 of 123 open modelscomposite 57.1/100 across 9 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Aider Polyglot | 56.9% | #7 / 18 | #31 / 69 |
| SciCode | 35.7% | #32 / 50 | #127 / 155 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU-Pro | 84.0% | #10 / 119 | #41 / 259 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 53.3% | #39 / 74 | #167 / 270 |
| MATH Level 5 | 93.0% | #2 / 32 | #19 / 108 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 69.2% | #30 / 83 | #164 / 291 |
| ARC-AGI | 15.8% | #12 / 16 | #174 / 200 |
| SimpleBench | 30.9% | #16 / 23 | #80 / 101 |
| CritPt | 1.1% | #27 / 50 | #110 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.