Model comparison

Llama 3.2 90B vs Mistral Large

Mistral Large is the stronger model overall, scoring 31.9 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 Large in 2 categories; 4 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Mistral Large leads 30.1 to 21.7.
The biggest single-benchmark swing is MATH Level 5: 39.4% for Llama 3.2 90B and 50.3% for Mistral Large.

Side by side

Llama 3.2 90B and Mistral Large specifications
	Llama 3.2 90B	Mistral Large
Provider	Meta	Mistral AI
Noometry Index	27.5	31.9
Released	2024-09-24	2024-02-26
Weights	Open	Open
Context window	—	131K
Max output	—	16K
Input $ / M tokens	—	$2
Output $ / M tokens	—	$6
Results tracked	9	51

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

Category by category

Coding Not comparable

Llama 3.2 90B: —, Mistral Large: 34.3 (#240)

Coding benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
SciCode	—	36.2%
BigCodeBench Instruct	—	30%
LiveBench Coding	—	47.1%
LMArena Coding	—	1277
BigCodeBench Complete	—	38.3%
ALE-Bench	—	264.7
HumanEval+	—	62.2%
MBPP+	—	59.5%

Agentic & Tool Use Llama 3.2 90B leads

Llama 3.2 90B: 30.0 (#80), Mistral Large: 28.6 (#89)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
Berkeley Function Calling Leaderboard	—	38.4%
BALROG	27.3%	—

Reasoning Llama 3.2 90B leads

Llama 3.2 90B: 21.7 (#217), Mistral Large: 15.8 (#310)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
Epoch Capabilities Index	125.5	128.52
SimpleBench	—	22.5%
CritPt	—	0%
EnigmaEval	0.4%	—
LiveBench Reasoning	—	43.5%
LMArena Hard Prompts	—	1257
DTBench	—	65.1%
LiveBench Data Analysis	—	50.1%
LMCA	—	16.7%
ForecastBench	—	57.1
LiveBench	—	48.4%

Math Mistral Large leads

Llama 3.2 90B: 11.1 (#308), Mistral Large: 18.2 (#291)

Math benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
OTIS Mock AIME 2024-2025	2.6%	8.5%
MATH Level 5	39.4%	50.3%
Omni-MATH	—	28.1%
LiveBench Math	—	42.5%
LMArena Math	—	1262
FrontierMath (Feb 2025 set)	—	0.3%

Knowledge Mistral Large leads

Llama 3.2 90B: 21.7 (#274), Mistral Large: 30.1 (#230)

Knowledge benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
GPQA Diamond	41%	51.3%
MMLU	80.3%	80%
MMLU-Pro	—	59.9%
Confabulations	—	21.4%
Vectara Hallucination Rate	—	4.5%
GPQA (HELM)	—	43.5%
LMArena Expert	—	1232

Multimodal Not comparable

Llama 3.2 90B: 25.4 (#124), Mistral Large: —

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

Multilingual Not comparable

Llama 3.2 90B: —, Mistral Large: 40.0 (#219)

Multilingual benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
LMArena Non-English	—	1237
LMArena Chinese	—	1240
LMArena French	—	1325
LMArena German	—	1254
LMArena Japanese	—	1188
LMArena Korean	—	1202
LMArena Russian	—	1257
LMArena Spanish	—	1268

Instruction Following Not comparable

Llama 3.2 90B: —, Mistral Large: 67.9 (#191)

Instruction Following benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
LiveBench Instruction Following	—	67.9%
IFEval	—	87.7%
LMArena Instruction Following	—	1249

Long Context Not comparable

Llama 3.2 90B: —, Mistral Large: 38.3 (#199)

Long Context benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
LMArena Longer Query	—	1261

Writing & Preference Not comparable

Llama 3.2 90B: —, Mistral Large: 40.7 (#242)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	Mistral Large
LMArena Text	—	1266
LMArena Creative Writing	—	1243
Short-Story Creative Writing	—	69%
EQ-Bench Creative Writing	—	985
WildBench	—	80.1%
LMArena Multi-Turn	—	1260
LiveBench Language	—	39.4%

Frequently asked questions

Is Llama 3.2 90B better than Mistral Large?