NVIDIA
Llama 3.1 Nemotron 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 #362 across 526
Rank #328 across 436
Rank #218 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 | 13.4 | #362 |
| Artificial Analysis Coding Index | coding | 10.8 | #328 |
| Artificial Analysis Math Index | math | 11.0 | #230 |
| MMLU-Pro | reasoning | 69.0% | #231 |
| reasoning |
| 46.5% |
| #382 |
| Humanity's Last Exam | reasoning | 4.6% | #368 |
| LiveCodeBench | coding | 16.9% | #283 |
| SciCode | coding, reasoning | 23.3% | #357 |
| MATH-500 | math | 73.3% | #133 |
| AIME | math | 24.7% | #94 |
| Output Speed | speed | 290.5 tok/s | #11 |
| Time to First Token | speed | 0.25s | #5 |
| Blended Price | cost | $1.20/M | #218 |
| Input Price | cost | $1.20/M | #249 |
| Output Price | cost | $1.20/M | #143 |
| Value Index | cost, overall | 11.2 | #262 |