DeepSeek R1 0528 — Benchmarks
Benchmark scores for DeepSeek R1 0528 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #11 of 123 open modelscomposite 69.5/100 across 7 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Aider Polyglot | 71.4% | #2 / 18 | #19 / 69 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU-Pro | 83.4% | #11 / 119 | #46 / 259 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 66.4% | #28 / 74 | #137 / 270 |
| MATH Level 5 | 96.6% | #1 / 32 | #9 / 108 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 76.3% | #23 / 83 | #132 / 291 |
| ARC-AGI | 21.2% | #11 / 16 | #163 / 200 |
| SimpleBench | 40.8% | #13 / 23 | #70 / 101 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.