DeepSeek R1 Distill Llama 70B — Benchmarks
Benchmark scores for DeepSeek R1 Distill Llama 70B 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 | 51.6 | #5 / 13 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| AIME 2024/2025 | 51.4% | #7 / 22 |
| MATH Level 5 | 89.9% | #3 / 23 |
| LiveBench Math | 58.1 | #6 / 13 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 55.7% | #10 / 28 |
| LiveBench Reasoning | 67.6 | #3 / 13 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.