Meta
Llama 3.2 Instruct 1B 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 #503 across 526
Rank #431 across 436
Rank #8 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 | 6.3 | #503 |
| Artificial Analysis Coding Index | coding | 0.6 | #431 |
| Artificial Analysis Math Index | math | 0.0 | #267 |
| MMLU-Pro | reasoning | 20.0% | #340 |
| reasoning |
| 19.6% |
| #501 |
| Humanity's Last Exam | reasoning | 5.3% | #288 |
| LiveCodeBench | coding | 1.9% | #340 |
| SciCode | coding, reasoning | 1.7% | #491 |
| MATH-500 | math | 14.0% | #199 |
| AIME | math | 0.0% | #189 |
| Output Speed | speed | 92.9 tok/s | #146 |
| Time to First Token | speed | 0.57s | #63 |
| Blended Price | cost | $0.050/M | #8 |
| Input Price | cost | $0.050/M | #22 |
| Output Price | cost | $0.050/M | #2 |
| Value Index | cost, overall | 126.0 | #40 |