Meta
Llama 3.2 Instruct 11B (Vision) 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 #519 across 526
Rank #395 across 436
Rank #82 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 | 3.3 | #519 |
| Artificial Analysis Coding Index | coding | 4.2 | #395 |
| Artificial Analysis Math Index | math | 1.7 | #261 |
| MMLU-Pro | reasoning | 46.4% | #305 |
| reasoning |
| 22.1% |
| #500 |
| Humanity's Last Exam | reasoning | 5.2% | #299 |
| LiveCodeBench | coding | 11.0% | #313 |
| SciCode | coding, reasoning | 11.2% | #438 |
| MATH-500 | math | 51.6% | #172 |
| AIME | math | 9.3% | #137 |
| Output Speed | speed | 87.4 tok/s | #154 |
| Time to First Token | speed | 0.56s | #61 |
| Blended Price | cost | $0.245/M | #82 |
| Input Price | cost | $0.245/M | #122 |
| Output Price | cost | $0.245/M | #37 |
| Value Index | cost, overall | 13.5 | #246 |