Model comparison

Llama 3.2 3B vs Palm 2

Palm 2 is the stronger model overall, scoring 29.4 to 28.4 on the Noometry Index.

Last verified October 10, 2026. 10 shared benchmarks.

Summary

They share 10 benchmarks with published results for both. Llama 3.2 3B scores higher in 5 categories and Palm 2 in 2 categories; 6 gaps are clear of the uncertainty.
The widest gap is in multilingual, where Llama 3.2 3B leads 26.4 to 21.1.
Llama 3.2 3B has downloadable open weights; the other is API-only.

Side by side

Llama 3.2 3B and Palm 2 specifications
	Llama 3.2 3B	Palm 2
Provider	Meta	Google
Noometry Index	28.4	29.4
Released	2024-09-24	—
Weights	Open	Proprietary
Context window	131K	—
Max output	118K	—
Input $ / M tokens	$0.05	—
Output $ / M tokens	$0.33	—
Results tracked	18	10

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

Category by category

Coding Palm 2 leads

Llama 3.2 3B: 27.1 (#314), Palm 2: 28.5 (#306)

Coding benchmarks
Benchmark	Llama 3.2 3B	Palm 2
LMArena Coding	1098	995
BigCodeBench Instruct	23.4%	—
BigCodeBench Complete	28.3%	—

Agentic & Tool Use Not comparable

Llama 3.2 3B: 19.9 (#135), Palm 2: —

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 3B	Palm 2
Berkeley Function Calling Leaderboard	21.9%	—
BALROG	10.1%	—

Reasoning Llama 3.2 3B leads

Llama 3.2 3B: 20.1 (#225), Palm 2: 18.2 (#270)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	Palm 2
LMArena Hard Prompts	1095	1005

Math Llama 3.2 3B leads

Llama 3.2 3B: 29.9 (#213), Palm 2: 28.4 (#229)

Math benchmarks
Benchmark	Llama 3.2 3B	Palm 2
LMArena Math	1126	1049

Knowledge Not comparable

Llama 3.2 3B: 29.1 (#232), Palm 2: —

Knowledge benchmarks
Benchmark	Llama 3.2 3B	Palm 2
LMArena Expert	1090	—

Multilingual Llama 3.2 3B leads

Llama 3.2 3B: 26.4 (#276), Palm 2: 21.1 (#290)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	Palm 2
LMArena Non-English	1019	916
LMArena Chinese	1017	887
LMArena German	1056	—
LMArena Russian	949	—

Instruction Following Llama 3.2 3B leads

Llama 3.2 3B: 56.3 (#270), Palm 2: 51.3 (#291)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	Palm 2
LMArena Instruction Following	1089	1010

Long Context Llama 3.2 3B leads

Llama 3.2 3B: 33.4 (#256), Palm 2: 30.7 (#280)

Long Context benchmarks
Benchmark	Llama 3.2 3B	Palm 2
LMArena Longer Query	1101	1010

Writing & Preference Too close to call

Llama 3.2 3B: 24.9 (#302), Palm 2: 25.7 (#299)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	Palm 2
LMArena Text	1110	1027
LMArena Creative Writing	1094	991
LMArena Multi-Turn	1105	994
EQ-Bench Creative Writing	595	—

Frequently asked questions

Is Llama 3.2 3B better than Palm 2?