Model comparison

Llama 3.2 90B vs Mistral Large 3

Mistral Large 3 is the stronger model overall, scoring 39.1 to 27.5 on the Noometry Index.

Last verified October 10, 2026. 1 shared benchmarks.

Summary

They share 1 benchmark with published results for both. Llama 3.2 90B scores higher in 1 category and Mistral Large 3 in 3 categories; 4 gaps are clear of the uncertainty.
The widest gap is in math, where Mistral Large 3 leads 38.7 to 11.1.

Side by side

Llama 3.2 90B and Mistral Large 3 specifications
	Llama 3.2 90B	Mistral Large 3
Provider	Meta	Mistral AI
Noometry Index	27.5	39.1
Released	2024-09-24	2025-12-02
Weights	Open	Open
Context window	—	262K
Max output	—	8K
Input $ / M tokens	—	$0.25
Output $ / M tokens	—	$0.75
Results tracked	9	24

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

Category by category

Coding Not comparable

Llama 3.2 90B: —, Mistral Large 3: 34.4 (#237)

Coding benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
LMArena WebDev	—	1230
LMArena Coding	—	1448

Agentic & Tool Use Not comparable

Llama 3.2 90B: 30.0 (#80), Mistral Large 3: —

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
BALROG	27.3%	—

Reasoning Llama 3.2 90B leads

Llama 3.2 90B: 21.7 (#217), Mistral Large 3: 15.2 (#319)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
Kagi LLM Benchmark	—	50.9%
NYT Connections (extended)	—	7.5%
EnigmaEval	0.4%	—
Thematic Generalization	—	23%
LMArena Hard Prompts	—	1429
Epoch Capabilities Index	125.5	—

Math Mistral Large 3 leads

Llama 3.2 90B: 11.1 (#308), Mistral Large 3: 38.7 (#129)

Math benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
OTIS Mock AIME 2024-2025	2.6%	—
LMArena Math	—	1414
MATH Level 5	39.4%	—

Knowledge Mistral Large 3 leads

Llama 3.2 90B: 21.7 (#274), Mistral Large 3: 36.0 (#177)

Knowledge benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
GPQA Diamond	41%	—
Vectara Hallucination Rate	—	14.5%
LMArena Expert	—	1421
MMLU	80.3%	—

Multimodal Mistral Large 3 leads

Llama 3.2 90B: 25.4 (#124), Mistral Large 3: 38.2 (#66)

Multimodal benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
LMArena Vision	1000	1221
GeoBench	52%	—

Multilingual Not comparable

Llama 3.2 90B: —, Mistral Large 3: 52.5 (#84)

Multilingual benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
LMArena Non-English	—	1413
LMArena Chinese	—	1447
LMArena French	—	1455
LMArena German	—	1437
LMArena Japanese	—	1394
LMArena Korean	—	1384
LMArena Russian	—	1411
LMArena Spanish	—	1440

Instruction Following Not comparable

Llama 3.2 90B: —, Mistral Large 3: 74.0 (#108)

Instruction Following benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
LMArena Instruction Following	—	1403

Long Context Not comparable

Llama 3.2 90B: —, Mistral Large 3: 43.1 (#105)

Long Context benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
LMArena Longer Query	—	1413

Writing & Preference Not comparable

Llama 3.2 90B: —, Mistral Large 3: 60.0 (#101)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	Mistral Large 3
LMArena Text	—	1428
LMArena Creative Writing	—	1386
EQ-Bench Creative Writing	—	1412
LMArena Multi-Turn	—	1429

Frequently asked questions

Is Llama 3.2 90B better than Mistral Large 3?