Model comparison

Granite 3.0 8b Instruct vs Llama 3.2 90B

Granite 3.0 8b Instruct is the stronger model overall, scoring 31.1 to 27.1 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Granite 3.0 8b Instruct IBM

31.1

Rank #266 Confirmed

Llama 3.2 90B

Summary

The widest gap is in math, where Granite 3.0 8b Instruct leads 30.3 to 10.4.

Side by side

Granite 3.0 8b Instruct and Llama 3.2 90B specifications
	Granite 3.0 8b Instruct	Llama 3.2 90B
Provider	IBM	Meta
Noometry Index	31.1	27.1
Released	—	2024-09-24
Weights	Open	Open
Context window	—	—
Max output	—	—
Input $ / M tokens	—	—
Output $ / M tokens	—	—
Results tracked	14	9

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

Category by category

Coding Not comparable

Granite 3.0 8b Instruct: 29.1 (#297), Llama 3.2 90B: —

Coding benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
BigCodeBench Instruct	29.3%	—
LMArena Coding	1113	—
BigCodeBench Complete	35.4%	—

Agentic & Tool Use Not comparable

Granite 3.0 8b Instruct: —, Llama 3.2 90B: 29.7 (#73)

Agentic & Tool Use benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
BALROG	—	27.3%

Reasoning Too close to call

Granite 3.0 8b Instruct: 20.0 (#227), Llama 3.2 90B: 20.9 (#207)

Reasoning benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
EnigmaEval	—	0.4%
LMArena Hard Prompts	1092	—
Epoch Capabilities Index	—	125.5

Math Granite 3.0 8b Instruct leads

Granite 3.0 8b Instruct: 30.3 (#211), Llama 3.2 90B: 10.4 (#302)

Math benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
OTIS Mock AIME 2024-2025	—	2.6%
LMArena Math	1143	—
MATH Level 5	—	39.4%

Knowledge Granite 3.0 8b Instruct leads

Granite 3.0 8b Instruct: 29.1 (#233), Llama 3.2 90B: 21.7 (#269)

Knowledge benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
GPQA Diamond	—	41%
LMArena Expert	1087	—
MMLU	—	80.3%

Multimodal Not comparable

Granite 3.0 8b Instruct: —, Llama 3.2 90B: 24.9 (#119)

Multimodal benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
LMArena Vision	—	1000
GeoBench	—	52%

Multilingual Not comparable

Granite 3.0 8b Instruct: 27.4 (#271), Llama 3.2 90B: —

Multilingual benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
LMArena Non-English	1037	—
LMArena Chinese	1063	—
LMArena Russian	1060	—

Instruction Following Not comparable

Granite 3.0 8b Instruct: 56.2 (#271), Llama 3.2 90B: —

Instruction Following benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
LMArena Instruction Following	1088	—

Long Context Not comparable

Granite 3.0 8b Instruct: 34.0 (#247), Llama 3.2 90B: —

Long Context benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
LMArena Longer Query	1122	—

Writing & Preference Not comparable

Granite 3.0 8b Instruct: 31.2 (#280), Llama 3.2 90B: —

Writing & Preference benchmarks
Benchmark	Granite 3.0 8b Instruct	Llama 3.2 90B
LMArena Text	1096	—
LMArena Creative Writing	1071	—
LMArena Multi-Turn	1063	—

Frequently asked questions

Is Granite 3.0 8b Instruct better than Llama 3.2 90B?