Model comparison

Llama 3.2 90B vs Wizardlm 70b

Wizardlm 70b is the stronger model overall, scoring 32.4 to 27.1 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Summary

The widest gap is in math, where Wizardlm 70b leads 29.7 to 10.4.

Side by side

Llama 3.2 90B and Wizardlm 70b specifications
	Llama 3.2 90B	Wizardlm 70b
Provider	Meta	Microsoft
Noometry Index	27.1	32.4
Released	2024-09-24	—
Weights	Open	Open
Context window	—	—
Max output	—	—
Input $ / M tokens	—	—
Output $ / M tokens	—	—
Results tracked	9	12

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

Category by category

Coding Not comparable

Llama 3.2 90B: —, Wizardlm 70b: 30.9 (#280)

Coding benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
LMArena Coding	—	1081

Agentic & Tool Use Not comparable

Llama 3.2 90B: 29.7 (#73), Wizardlm 70b: —

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
BALROG	27.3%	—

Reasoning Llama 3.2 90B leads

Llama 3.2 90B: 20.9 (#207), Wizardlm 70b: 19.8 (#231)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
EnigmaEval	0.4%	—
LMArena Hard Prompts	—	1079
Epoch Capabilities Index	125.5	—

Math Wizardlm 70b leads

Llama 3.2 90B: 10.4 (#302), Wizardlm 70b: 29.7 (#216)

Math benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
OTIS Mock AIME 2024-2025	2.6%	—
LMArena Math	—	1116
MATH Level 5	39.4%	—

Knowledge Not comparable

Llama 3.2 90B: 21.7 (#269), Wizardlm 70b: —

Knowledge benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
GPQA Diamond	41%	—
MMLU	80.3%	—

Multimodal Not comparable

Llama 3.2 90B: 24.9 (#119), Wizardlm 70b: —

Multimodal benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
LMArena Vision	1000	—
GeoBench	52%	—

Multilingual Not comparable

Llama 3.2 90B: —, Wizardlm 70b: 29.8 (#260)

Multilingual benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
LMArena Non-English	—	1078
LMArena Chinese	—	1052
LMArena German	—	1083
LMArena Russian	—	1155

Instruction Following Not comparable

Llama 3.2 90B: —, Wizardlm 70b: 56.5 (#268)

Instruction Following benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
LMArena Instruction Following	—	1093

Long Context Not comparable

Llama 3.2 90B: —, Wizardlm 70b: 33.3 (#258)

Long Context benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
LMArena Longer Query	—	1097

Writing & Preference Not comparable

Llama 3.2 90B: —, Wizardlm 70b: 34.9 (#264)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	Wizardlm 70b
LMArena Text	—	1120
LMArena Creative Writing	—	1149
LMArena Multi-Turn	—	1108

Frequently asked questions

Is Llama 3.2 90B better than Wizardlm 70b?