DeepSeek
DeepSeek-R1-Distill-Llama-70B benchmark results
4 results on 4 benchmarks from 2 sources.
Open weights Released: Jan 20, 2025 Updated Oct 22, 2026
Also listed as: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| Open LLM Leaderboard v2 | 27.8% | 1320 | Average of 6 normalised benchmarks; bfloat16; 70.554B params“deepseek-ai/DeepSeek-R1-Distill-Llama-70B” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 55.7% | 192 | Epoch AI run, accuracy | Independent run | Mar 10, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 51.4% | 166 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Mar 7, 2025 |
| MATH Level 5 | 89.9% | 23 | Epoch AI run, accuracy | Independent run | Mar 10, 2025 |
FAQ
Where do these DeepSeek-R1-Distill-Llama-70B scores come from?
From Epoch AI Benchmarking Hub and Hugging Face Open LLM Leaderboard v2 (archived). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.