Model comparison

Llama 3.2 90B vs Mistral Medium

Mistral Medium is the stronger model overall, scoring 36.3 to 27.5 on the Noometry Index.

Last verified October 10, 2026. 4 shared benchmarks.

Summary

They share 4 benchmarks with published results for both. Llama 3.2 90B scores higher in 1 category and Mistral Medium in 4 categories; 5 gaps are clear of the uncertainty.
The widest gap is in math, where Mistral Medium leads 28.1 to 11.1.
The biggest single-benchmark swing is MATH Level 5: 39.4% for Llama 3.2 90B and 81.6% for Mistral Medium.

Side by side

Llama 3.2 90B and Mistral Medium specifications
	Llama 3.2 90B	Mistral Medium
Provider	Meta	Mistral AI
Noometry Index	27.5	36.3
Released	2024-09-24	2023-12-11
Weights	Open	Open
Context window	—	262K
Max output	—	262K
Input $ / M tokens	—	$1.50
Output $ / M tokens	—	$7.50
Results tracked	9	36

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

Category by category

Coding Not comparable

Llama 3.2 90B: —, Mistral Medium: 34.2 (#243)

Coding benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
FrontierCode	—	8%
SciCode	—	40.2%
WeirdML	—	43.7%
LMArena Coding	—	1434
ALE-Bench	—	763.98

Agentic & Tool Use Llama 3.2 90B leads

Llama 3.2 90B: 30.0 (#80), Mistral Medium: 28.3 (#90)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
Berkeley Function Calling Leaderboard	—	37.7%
BALROG	27.3%	—

Reasoning Mistral Medium leads

Llama 3.2 90B: 21.7 (#217), Mistral Medium: 24.0 (#167)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
Kagi LLM Benchmark	—	50%
CritPt	—	0%
EnigmaEval	0.4%	—
LMArena Hard Prompts	—	1426
DTBench	—	75.5%
LMCA	—	26.1%
Surface Evolver Bench	—	26.9%
Epoch Capabilities Index	125.5	—

Math Mistral Medium leads

Llama 3.2 90B: 11.1 (#308), Mistral Medium: 28.1 (#245)

Math benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
OTIS Mock AIME 2024-2025	2.6%	32.2%
MATH Level 5	39.4%	81.6%
ProofBench	—	9%
LMArena Math	—	1408
FrontierMath (Feb 2025 set)	—	0.3%

Knowledge Mistral Medium leads

Llama 3.2 90B: 21.7 (#274), Mistral Medium: 25.0 (#265)

Knowledge benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
GPQA Diamond	41%	59.5%
Humanity's Last Exam	—	4.5%
Vectara Hallucination Rate	—	22.7%
LMArena Expert	—	1408
MMLU	80.3%	—

Multimodal Mistral Medium leads

Llama 3.2 90B: 25.4 (#124), Mistral Medium: 35.3 (#88)

Multimodal benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
LMArena Vision	1000	1172
GeoBench	52%	—

Multilingual Not comparable

Llama 3.2 90B: —, Mistral Medium: 52.1 (#91)

Multilingual benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
LMArena Non-English	—	1408
LMArena Chinese	—	1447
LMArena French	—	1459
LMArena German	—	1432
LMArena Japanese	—	1378
LMArena Korean	—	1380
LMArena Russian	—	1411
LMArena Spanish	—	1433

Instruction Following Not comparable

Llama 3.2 90B: —, Mistral Medium: 73.7 (#116)

Instruction Following benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
LMArena Instruction Following	—	1398

Long Context Not comparable

Llama 3.2 90B: —, Mistral Medium: 42.9 (#114)

Long Context benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
LMArena Longer Query	—	1406

Writing & Preference Not comparable

Llama 3.2 90B: —, Mistral Medium: 60.0 (#103)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	Mistral Medium
LMArena Text	—	1424
LMArena Creative Writing	—	1391
Short-Story Creative Writing	—	77.3%
LMArena Multi-Turn	—	1418

Frequently asked questions

Is Llama 3.2 90B better than Mistral Medium?