Llama 3.2 90B Vision

Meta · meta/llama-3-2-90b-vision

ProviderMeta
Familyllama
Typevlm
Statusactive
Released2024-09-19

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
AI2D (AI2 Diagrams)unassessed92.3
BBQ (Bias Benchmark for QA)unassessed79.8
ChartQAunassessed85.5
DocVQAunassessed90.1
HELM Safetyunassessed84.5
MathVistaunassessed57.3
MMMUunassessed60.3
ToxiGenunassessed87.5

Data

This card as JSON · Edit on GitHub