Llama 3.2 90B Vision Instruct — Benchmarks
Benchmark scores for Llama 3.2 90B Vision Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Knowledge
| Benchmark | Score | Rank |
|---|---|---|
| MMLU | 80.3% | #8 / 74 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| AIME 2024/2025 | 2.6% | #23 / 29 |
| MATH Level 5 | 39.4% | #16 / 31 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 41.0% | #25 / 41 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.