Model comparison

Gemma 3n E4b IT vs Llama 3.2 90B

Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 27.5 on the Noometry Index.

Last verified October 11, 2026. 0 shared benchmarks.

Gemma 3n E4b IT

Google

37.3

Rank #206 Confirmed

Llama 3.2 90B

Summary

The widest gap is in math, where Gemma 3n E4b IT leads 35.1 to 11.1.

Side by side

Gemma 3n E4b IT and Llama 3.2 90B specifications
	Gemma 3n E4b IT	Llama 3.2 90B
Provider	Google	Meta
Noometry Index	37.3	27.5
Released	—	2024-09-24
Weights	Open	Open
Context window	—	—
Max output	—	—
Input $ / M tokens	—	—
Output $ / M tokens	—	—
Results tracked	18	9

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

Category by category

Coding Not comparable

Gemma 3n E4b IT: 37.0 (#198), Llama 3.2 90B: —

Coding benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
LMArena Coding	1268	—

Agentic & Tool Use Not comparable

Gemma 3n E4b IT: —, Llama 3.2 90B: 30.0 (#80)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
BALROG	—	27.3%

Reasoning Llama 3.2 90B leads

Gemma 3n E4b IT: 19.9 (#247), Llama 3.2 90B: 21.7 (#217)

Reasoning benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
Kagi LLM Benchmark	31.5%	—
EnigmaEval	—	0.4%
LMArena Hard Prompts	1284	—
Epoch Capabilities Index	—	125.5

Math Gemma 3n E4b IT leads

Gemma 3n E4b IT: 35.1 (#188), Llama 3.2 90B: 11.1 (#308)

Math benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
OTIS Mock AIME 2024-2025	—	2.6%
LMArena Math	1251	—
MATH Level 5	—	39.4%

Knowledge Gemma 3n E4b IT leads

Gemma 3n E4b IT: 34.2 (#198), Llama 3.2 90B: 21.7 (#274)

Knowledge benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
GPQA Diamond	—	41%
LMArena Expert	1246	—
MMLU	—	80.3%

Multimodal Not comparable

Gemma 3n E4b IT: —, Llama 3.2 90B: 25.4 (#124)

Multimodal benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
LMArena Vision	—	1000
GeoBench	—	52%

Multilingual Not comparable

Gemma 3n E4b IT: 43.4 (#183), Llama 3.2 90B: —

Multilingual benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
LMArena Non-English	1285	—
LMArena Chinese	1309	—
LMArena French	1330	—
LMArena German	1311	—
LMArena Japanese	1272	—
LMArena Korean	1259	—
LMArena Russian	1288	—
LMArena Spanish	1305	—

Instruction Following Not comparable

Gemma 3n E4b IT: 66.1 (#210), Llama 3.2 90B: —

Instruction Following benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
LMArena Instruction Following	1255	—

Long Context Not comparable

Gemma 3n E4b IT: 38.7 (#191), Llama 3.2 90B: —

Long Context benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
LMArena Longer Query	1276	—

Writing & Preference Not comparable

Gemma 3n E4b IT: 50.1 (#186), Llama 3.2 90B: —

Writing & Preference benchmarks
Benchmark	Gemma 3n E4b IT	Llama 3.2 90B
LMArena Text	1306	—
LMArena Creative Writing	1287	—
LMArena Multi-Turn	1276	—

Frequently asked questions

Is Gemma 3n E4b IT better than Llama 3.2 90B?