Meta
Llama 3.1 Instruct 8B 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 #404 across 526
Rank #388 across 436
Rank #25 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 | 11.8 | #404 |
| Artificial Analysis Coding Index | coding | 4.9 | #388 |
| Artificial Analysis Math Index | math | 4.3 | #249 |
| MMLU-Pro | reasoning | 47.6% | #301 |
| reasoning |
| 25.9% |
| #486 |
| Humanity's Last Exam | reasoning | 5.1% | #313 |
| LiveCodeBench | coding | 11.6% | #307 |
| SciCode | coding, reasoning | 13.2% | #427 |
| MATH-500 | math | 51.9% | #171 |
| AIME | math | 7.7% | #145 |
| Output Speed | speed | 201.5 tok/s | #35 |
| Time to First Token | speed | 0.51s | #41 |
| Blended Price | cost | $0.100/M | #25 |
| Input Price | cost | $0.100/M | #47 |
| Output Price | cost | $0.100/M | #7 |
| Value Index | cost, overall | 118.0 | #46 |