Model comparison

Llama 3.2 90B vs Pixtral Large

Pixtral Large is the stronger model overall, scoring 32.2 to 27.5 on the Noometry Index.

Last verified October 11, 2026. 2 shared benchmarks.

Summary

They share 2 benchmarks with published results for both. Llama 3.2 90B scores higher in 0 categories and Pixtral Large in 2 categories; one gap is clear of the uncertainty.
The widest gap is in multimodal, where Pixtral Large leads 30.6 to 25.4.

Sponsored placements are available on pages like this one. Advertise on Noometry

Llama 3.2 90B: 30.0 (#80), Pixtral Large: —

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	Pixtral Large
BALROG	27.3%	—

Llama 3.2 90B: 21.7 (#217), Pixtral Large: 21.7 (#218)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	Pixtral Large
EnigmaEval	0.4%	0.8%
Epoch Capabilities Index	125.5	—

Llama 3.2 90B: 11.1 (#308), Pixtral Large: —

Math benchmarks
Benchmark	Llama 3.2 90B	Pixtral Large
OTIS Mock AIME 2024-2025	2.6%	—
MATH Level 5	39.4%	—

Llama 3.2 90B: 21.7 (#274), Pixtral Large: —

Knowledge benchmarks
Benchmark	Llama 3.2 90B	Pixtral Large
GPQA Diamond	41%	—
MMLU	80.3%	—

Llama 3.2 90B: 25.4 (#124), Pixtral Large: 30.6 (#111)

Multimodal benchmarks
Benchmark	Llama 3.2 90B	Pixtral Large
LMArena Vision	1000	1089
GeoBench	52%	—

Llama 3.2 90B: —, Pixtral Large: 32.9 (#278)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	Pixtral Large
EQ-Bench Creative Writing	—	988

Pixtral Large is the stronger model overall, scoring 32.2 to 27.5 on the Noometry Index.

2 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Pixtral Large has 3.