Llama 3.2 90B Vision: benchmark results
Provider: Meta.
Aggregate Rating 1488 ± 31, rank #2535 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CharXiv-R | 37.5 | Validation chart-visible reasoning accuracy (%) | 71.3 |
| CharXiv-D | 68.42 | Score (%) | 64.4 |
| MMVU | 47.6 | Hidden-test overall accuracy, chain-of-thought (%) | 57.1 |
| SeePhys | 11.7 | Total Accuracy (%) | 38.1 |
| MaCBench | 0.36 | Overall Score (score) | 20 |
| GeoBench ACW | 2797.56 | Average Score | 11.8 |
| VerdictBench | 40.9 | Accuracy (self-reported) | 0 |
Interactive version: theaggregate.ai/model?slug=llama-3-2-90b-vision · How It Works · Data refreshed daily, snapshot 2026-11-08.