Model comparison

Granite 3.1 2b Instruct vs Llama 3.2 90B

Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 27.1 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Granite 3.1 2b Instruct IBM

32.6

Rank #243 Confirmed

Llama 3.2 90B

Summary

The widest gap is in math, where Granite 3.1 2b Instruct leads 30.6 to 10.4.

Side by side

Granite 3.1 2b Instruct and Llama 3.2 90B specifications
	Granite 3.1 2b Instruct	Llama 3.2 90B
Provider	IBM	Meta
Noometry Index	32.6	27.1
Released	—	2024-09-24
Weights	Open	Open
Context window	—	—
Max output	—	—
Input $ / M tokens	—	—
Output $ / M tokens	—	—
Results tracked	12	9

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

Category by category

Coding Not comparable

Granite 3.1 2b Instruct: 32.9 (#255), Llama 3.2 90B: —

Coding benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
LMArena Coding	1149	—

Agentic & Tool Use Not comparable

Granite 3.1 2b Instruct: —, Llama 3.2 90B: 29.7 (#73)

Agentic & Tool Use benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
BALROG	—	27.3%

Reasoning Too close to call

Granite 3.1 2b Instruct: 21.0 (#206), Llama 3.2 90B: 20.9 (#207)

Reasoning benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
EnigmaEval	—	0.4%
LMArena Hard Prompts	1138	—
Epoch Capabilities Index	—	125.5

Math Granite 3.1 2b Instruct leads

Granite 3.1 2b Instruct: 30.6 (#206), Llama 3.2 90B: 10.4 (#302)

Math benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
OTIS Mock AIME 2024-2025	—	2.6%
LMArena Math	1159	—
MATH Level 5	—	39.4%

Knowledge Granite 3.1 2b Instruct leads

Granite 3.1 2b Instruct: 30.3 (#223), Llama 3.2 90B: 21.7 (#269)

Knowledge benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
GPQA Diamond	—	41%
LMArena Expert	1131	—
MMLU	—	80.3%

Multimodal Not comparable

Granite 3.1 2b Instruct: —, Llama 3.2 90B: 24.9 (#119)

Multimodal benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
LMArena Vision	—	1000
GeoBench	—	52%

Multilingual Not comparable

Granite 3.1 2b Instruct: 29.2 (#264), Llama 3.2 90B: —

Multilingual benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
LMArena Non-English	1068	—
LMArena Chinese	1138	—
LMArena Russian	1063	—

Instruction Following Not comparable

Granite 3.1 2b Instruct: 58.0 (#259), Llama 3.2 90B: —

Instruction Following benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
LMArena Instruction Following	1116	—

Long Context Not comparable

Granite 3.1 2b Instruct: 35.0 (#239), Llama 3.2 90B: —

Long Context benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
LMArena Longer Query	1155	—

Writing & Preference Not comparable

Granite 3.1 2b Instruct: 34.3 (#269), Llama 3.2 90B: —

Writing & Preference benchmarks
Benchmark	Granite 3.1 2b Instruct	Llama 3.2 90B
LMArena Text	1127	—
LMArena Creative Writing	1116	—
LMArena Multi-Turn	1099	—

Frequently asked questions

Is Granite 3.1 2b Instruct better than Llama 3.2 90B?