Rankings / Meta AI
Llama 3.2 90B Vision Instruct
released 2024-09-24
BenchAtlas Index
as of 2026-07-14
base configuration
rank #396
5 families · 3 categories · medium
Benchmark evidence
7 results
external indices
| ECI | 125.7 points | independent | Epoch AI Benchmarking Hub |
factuality
| MASK | 54.1 % 51.8–56.3 | independent | Scale Labs |
knowledge science
| GPQA Diamond | 41.0 % | independent | Epoch AI Benchmarking Hub 2025-01-27 |
multimodal
| VISTA | 24.6 % 23.8–25.4 | independent | Scale Labs |
reasoning math
| EnigmaEval | 0.4 % 0.0–0.7 | independent | Scale Labs | |
| MATH Level 5 | 39.4 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| OTIS Mock AIME 2024–2025 | 2.6 % | independent | Epoch AI Benchmarking Hub 2025-02-25 |