Model comparison

Granite 4.2 3b vs Llama 3.2 90B

Granite 4.2 3b is the stronger model overall, scoring 39.0 to 27.1 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Granite 4.2 3b IBM

39.0

Rank #163 Confirmed

Llama 3.2 90B

Summary

The widest gap is in knowledge, where Granite 4.2 3b leads 35.6 to 21.7.

Side by side

Granite 4.2 3b and Llama 3.2 90B specifications
	Granite 4.2 3b	Llama 3.2 90B
Provider	IBM	Meta
Noometry Index	39.0	27.1
Released	—	2024-09-24
Weights	Open	Open
Context window	—	—
Max output	—	—
Input $ / M tokens	—	—
Output $ / M tokens	—	—
Results tracked	11	9

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

Category by category

Coding Not comparable

Granite 4.2 3b: 39.4 (#146), Llama 3.2 90B: —

Coding benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
LMArena Coding	1363	—

Agentic & Tool Use Not comparable

Granite 4.2 3b: —, Llama 3.2 90B: 29.7 (#73)

Agentic & Tool Use benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
BALROG	—	27.3%

Reasoning Granite 4.2 3b leads

Granite 4.2 3b: 25.0 (#136), Llama 3.2 90B: 20.9 (#207)

Reasoning benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
EnigmaEval	—	0.4%
LMArena Hard Prompts	1308	—
Epoch Capabilities Index	—	125.5

Math Not comparable

Granite 4.2 3b: —, Llama 3.2 90B: 10.4 (#302)

Math benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
OTIS Mock AIME 2024-2025	—	2.6%
MATH Level 5	—	39.4%

Knowledge Granite 4.2 3b leads

Granite 4.2 3b: 35.6 (#169), Llama 3.2 90B: 21.7 (#269)

Knowledge benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
GPQA Diamond	—	41%
LMArena Expert	1313	—
MMLU	—	80.3%

Multimodal Not comparable

Granite 4.2 3b: —, Llama 3.2 90B: 24.9 (#119)

Multimodal benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
LMArena Vision	—	1000
GeoBench	—	52%

Multilingual Not comparable

Granite 4.2 3b: 42.4 (#193), Llama 3.2 90B: —

Multilingual benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
LMArena Non-English	1268	—
LMArena Chinese	1268	—
LMArena Russian	1249	—

Instruction Following Not comparable

Granite 4.2 3b: 67.2 (#195), Llama 3.2 90B: —

Instruction Following benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
LMArena Instruction Following	1271	—

Long Context Not comparable

Granite 4.2 3b: 39.3 (#179), Llama 3.2 90B: —

Long Context benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
LMArena Longer Query	1293	—

Writing & Preference Not comparable

Granite 4.2 3b: 47.9 (#202), Llama 3.2 90B: —

Writing & Preference benchmarks
Benchmark	Granite 4.2 3b	Llama 3.2 90B
LMArena Text	1295	—
LMArena Creative Writing	1215	—
LMArena Multi-Turn	1293	—

Frequently asked questions

Is Granite 4.2 3b better than Llama 3.2 90B?