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.
Coding
| Benchmark | Score | Rank |
|---|---|---|
| Aider Polyglot | 71.4% | #1 / 12 |
Knowledge
| Benchmark | Score | Rank |
|---|---|---|
| SimpleQA | 27.4% | #4 / 4 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| AIME 2024/2025 | 66.4% | #5 / 22 |
| MATH Level 5 | 96.6% | #1 / 23 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 76.3% | #5 / 28 |
| ARC-AGI | 21.2% | #3 / 7 |
| SimpleBench | 40.8% | #4 / 10 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.