Meta
Llama 3.1 Instruct 70B is a Meta Llama 3 family model, part of Meta's widely deployed open-weight LLM series for assistants, retrieval, coding, and self-hosted applications. The profile helps compare this specific size and instruction variant with newer open and proprietary models in the local snapshot.
Introducing Meta Llama 3Rank #386 across 526
Rank #325 across 436
Rank #151 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 | 12.5 | #386 |
| Artificial Analysis Coding Index | coding | 10.9 | #325 |
| Artificial Analysis Math Index | math | 4.0 | #251 |
| MMLU-Pro | reasoning | 67.6% | #239 |
| reasoning |
| 40.9% |
| #411 |
| Humanity's Last Exam | reasoning | 4.6% | #367 |
| LiveCodeBench | coding | 23.2% | #262 |
| SciCode | coding, reasoning | 26.7% | #318 |
| MATH-500 | math | 64.9% | #155 |
| AIME | math | 17.3% | #107 |
| Output Speed | speed | 43.3 tok/s | #266 |
| Time to First Token | speed | 0.54s | #51 |
| Blended Price | cost | $0.560/M | #151 |
| Input Price | cost | $0.560/M | #202 |
| Output Price | cost | $0.560/M | #94 |
| Value Index | cost, overall | 22.3 | #213 |