What are Llama 3.2 90B Vision's benchmark scores?

As of 25 Oct 2026, Llama 3.2 90B Vision scores 36.9 ±5.4 on the BenchLeader Index, strongest in composite (37) and weakest in multimodal (23). That rests on 7 independent benchmark results, and every score on this page links to its publisher.

How does Llama 3.2 90B Vision rank?

Llama 3.2 90B Vision is #742 of 785 ranked configurations on 25 Oct 2026. 202 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was Llama 3.2 90B Vision released?

Meta released Llama 3.2 90B Vision on 24 Sept 2024.

Meta Open weights: meta-llama/Llama-3.2-90B-Vision-Instruct Compare with another model

Llama 3.2 90B Vision

Llama 3.2 90B Vision is a Meta open-weights model, released 24 Sept 2024. Its best configuration ranks #742 of 785 on the BenchLeader Index at 36.9 ±5.4, in the lower half. The ± is the point: 202 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (37) and lowest in multimodal (23). Last measured 19 Oct 2026.

Blended price: –
Output speed: –
First answer: –
Context: 128k
Full answer: –
Cost per run: –
Released: 24 Sept 2024

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index37
Reasoning32
Maths33
Multimodal23
Composite37

How its index has moved

9 Sept 2026 to 20 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	not stated	Source
GPQA Diamond	41.0%#245	Epoch AI Benchmarking Hub
GPQA Diamond (AA)not in index	43.2%#461	Artificial Analysis
Humanity's Last Exam (AA)not in index	4.5%#498	Artificial Analysis

Agents & tools

Benchmark	not stated	Source
BALROGnot in index	27.3%#21	BALROG

Maths

Benchmark	not stated	Source
OTIS Mock AIME	2.6%#254	Epoch AI Benchmarking Hub
MATH Level 5	39.4%#64	Epoch AI Benchmarking Hub

Knowledge

Benchmark	not stated	Source
MMLUnot in index	80.3%#18	Epoch AI Benchmarking Hub

Multimodal

Benchmark	not stated	Source
Arena Vision	1000#141	Arena (LMArena)
MMMU-Pro	39.5%#266	Artificial Analysis
VISTA	24.6%#55	Scale AI SEAL
GeoBenchnot in index	52.0%#20	GeoBench

Composite

Benchmark	not stated	Source
AA Intelligence Index v4.3.2	6.4#531	Artificial Analysis

Safety & honesty

Benchmark	not stated	Source
MASKnot in index	54.1%#45	Scale AI SEAL

New this month

Questions people ask

What are Llama 3.2 90B Vision's benchmark scores?: As of 25 Oct 2026, Llama 3.2 90B Vision scores 36.9 ±5.4 on the BenchLeader Index, strongest in composite (37) and weakest in multimodal (23). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
How does Llama 3.2 90B Vision rank?: Llama 3.2 90B Vision is #742 of 785 ranked configurations on 25 Oct 2026. 202 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Llama 3.2 90B Vision released?: Meta released Llama 3.2 90B Vision on 24 Sept 2024.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Llama 3.2 90B Vision: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/llama-3-2-90b-vision.