DeepSeek
DeepSeek R1 Distill Llama 70B is a DeepSeek model profile, from a family known for strong reasoning, coding, and cost-conscious API models such as R1 and V-series releases. This page separates the public release context from measured benchmark performance so you can inspect its quality and efficiency directly.
DeepSeek release notesRank #303 across 526
Rank #315 across 436
Rank #174 across 357
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 16.0 | #303 |
| Artificial Analysis Coding Index | coding | 11.4 | #315 |
| Artificial Analysis Math Index | math | 53.7 | #133 |
| MMLU-Pro | reasoning | 79.5% | #123 |
| reasoning |
| 40.2% |
| #415 |
| Humanity's Last Exam | reasoning | 6.1% | #255 |
| LiveCodeBench | coding | 26.6% | #247 |
| SciCode | coding, reasoning | 31.3% | #250 |
| MATH-500 | math | 93.5% | #52 |
| AIME | math | 67.0% | #46 |
| Output Speed | speed | 44.7 tok/s | #260 |
| Time to First Token | speed | 0.32s | #13 |
| Blended Price | cost | $0.787/M | #174 |
| Input Price | cost | $0.700/M | #223 |
| Output Price | cost | $1.05/M | #136 |
| Value Index | cost, overall | 20.3 | #219 |