Model comparison

Llama 3.2 90B vs Mistral Small

Mistral Small is the stronger model overall, scoring 33.4 to 27.5 on the Noometry Index.

Last verified October 10, 2026. 5 shared benchmarks.

Summary

They share 5 benchmarks with published results for both. Llama 3.2 90B scores higher in 2 categories and Mistral Small in 3 categories; 5 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Mistral Small leads 31.0 to 21.7.
The biggest single-benchmark swing is MATH Level 5: 39.4% for Llama 3.2 90B and 46.8% for Mistral Small.

Side by side

Llama 3.2 90B and Mistral Small specifications
	Llama 3.2 90B	Mistral Small
Provider	Meta	Mistral AI
Noometry Index	27.5	33.4
Released	2024-09-24	2024-02-26
Weights	Open	Open
Context window	—	262K
Max output	—	256K
Input $ / M tokens	—	$0.15
Output $ / M tokens	—	$0.60
Results tracked	9	39

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

Category by category

Coding Not comparable

Llama 3.2 90B: —, Mistral Small: 34.0 (#247)

Coding benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
SciCode	—	26.5%
BigCodeBench Instruct	—	36.1%
LiveBench Coding	—	36.2%
LMArena Coding	—	1362
BigCodeBench Complete	—	46.6%
ALE-Bench	—	497.62

Agentic & Tool Use Llama 3.2 90B leads

Llama 3.2 90B: 30.0 (#80), Mistral Small: 28.1 (#93)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
Berkeley Function Calling Leaderboard	—	37.1%
BALROG	27.3%	—

Reasoning Llama 3.2 90B leads

Llama 3.2 90B: 21.7 (#217), Mistral Small: 19.8 (#250)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
Kagi LLM Benchmark	—	37.8%
CritPt	—	0%
EnigmaEval	0.4%	—
LiveBench Reasoning	—	44.8%
LMArena Hard Prompts	—	1335
DTBench	—	70.9%
LiveBench Data Analysis	—	53.7%
LMCA	—	20.6%
Epoch Capabilities Index	125.5	—
LiveBench	—	44%

Math Mistral Small leads

Llama 3.2 90B: 11.1 (#308), Mistral Small: 16.4 (#293)

Math benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
OTIS Mock AIME 2024-2025	2.6%	5.8%
MATH Level 5	39.4%	46.8%
LiveBench Math	—	39.9%
LMArena Math	—	1341

Knowledge Mistral Small leads

Llama 3.2 90B: 21.7 (#274), Mistral Small: 31.0 (#222)

Knowledge benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
GPQA Diamond	41%	47.5%
MMLU	80.3%	68.7%
Vectara Hallucination Rate	—	5.1%
LMArena Expert	—	1291

Multimodal Mistral Small leads

Llama 3.2 90B: 25.4 (#124), Mistral Small: 33.5 (#96)

Multimodal benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
LMArena Vision	1000	1142
GeoBench	52%	—

Multilingual Not comparable

Llama 3.2 90B: —, Mistral Small: 45.5 (#169)

Multilingual benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
LMArena Non-English	—	1315
LMArena Chinese	—	1340
LMArena French	—	1337
LMArena German	—	1340
LMArena Japanese	—	1275
LMArena Korean	—	1259
LMArena Russian	—	1324
LMArena Spanish	—	1346

Instruction Following Not comparable

Llama 3.2 90B: —, Mistral Small: 66.4 (#209)

Instruction Following benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
LiveBench Instruction Following	—	63.7%
LMArena Instruction Following	—	1310

Long Context Not comparable

Llama 3.2 90B: —, Mistral Small: 40.4 (#156)

Long Context benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
LMArena Longer Query	—	1327

Writing & Preference Not comparable

Llama 3.2 90B: —, Mistral Small: 52.5 (#171)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	Mistral Small
LMArena Text	—	1338
LMArena Creative Writing	—	1305
LMArena Multi-Turn	—	1344
LiveBench Language	—	30.5%

Frequently asked questions

Is Llama 3.2 90B better than Mistral Small?