Model comparison

Llama 3.2 3B vs Nova 2 Lite

Nova 2 Lite is the stronger model overall, scoring 39.7 to 28.9 on the Noometry Index. Llama 3.2 3B costs 7.1× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.

Last verified October 10, 2026. 14 shared benchmarks.

Llama 3.2 3B

Summary

They share 14 benchmarks with published results for both. Llama 3.2 3B scores higher in 0 categories and Nova 2 Lite in 9 categories; 9 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Nova 2 Lite leads 53.9 to 24.7.
The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 21.9% for Llama 3.2 3B and 27.1% for Nova 2 Lite.
Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
Nova 2 Lite accepts more context: 1M tokens versus 131K.
Llama 3.2 3B has downloadable open weights; the other is API-only.

Side by side

Llama 3.2 3B and Nova 2 Lite specifications
	Llama 3.2 3B	Nova 2 Lite
Provider	Meta	Amazon
Noometry Index	28.9	39.7
Released	2024-09-24	2025-12-01
Weights	Open	Proprietary
Context window	131K	1M
Max output	118K	64K
Input $ / M tokens	$0.05	$0.30
Output $ / M tokens	$0.33	$2.50
Results tracked	18	19

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

Category by category

Coding Nova 2 Lite leads

Llama 3.2 3B: 27.6 (#319), Nova 2 Lite: 40.7 (#134)

Coding benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
LMArena Coding	1098	1385
BigCodeBench Instruct	23.4%	—
BigCodeBench Complete	28.3%	—

Agentic & Tool Use Nova 2 Lite leads

Llama 3.2 3B: 20.1 (#143), Nova 2 Lite: 24.1 (#121)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
Berkeley Function Calling Leaderboard	21.9%	27.1%
BALROG	10.1%	—

Reasoning Nova 2 Lite leads

Llama 3.2 3B: 21.0 (#228), Nova 2 Lite: 27.5 (#118)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
LMArena Hard Prompts	1095	1364

Math Nova 2 Lite leads

Llama 3.2 3B: 32.4 (#214), Nova 2 Lite: 37.5 (#156)

Math benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
LMArena Math	1126	1359

Knowledge Nova 2 Lite leads

Llama 3.2 3B: 29.7 (#235), Nova 2 Lite: 43.0 (#94)

Knowledge benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
LMArena Expert	1090	1358
Vectara Hallucination Rate	—	5.1%

Multilingual Nova 2 Lite leads

Llama 3.2 3B: 26.2 (#281), Nova 2 Lite: 47.1 (#153)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
LMArena Non-English	1019	1337
LMArena Chinese	1017	1364
LMArena German	1056	1343
LMArena Russian	949	1343
LMArena French	—	1381
LMArena Japanese	—	1271
LMArena Korean	—	1284
LMArena Spanish	—	1373

Instruction Following Nova 2 Lite leads

Llama 3.2 3B: 56.0 (#275), Nova 2 Lite: 70.5 (#161)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
LMArena Instruction Following	1089	1335

Long Context Nova 2 Lite leads

Llama 3.2 3B: 33.4 (#261), Nova 2 Lite: 40.6 (#150)

Long Context benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
LMArena Longer Query	1100	1335

Writing & Preference Nova 2 Lite leads

Llama 3.2 3B: 24.7 (#307), Nova 2 Lite: 53.9 (#154)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	Nova 2 Lite
LMArena Text	1110	1362
LMArena Creative Writing	1094	1291
LMArena Multi-Turn	1105	1338
EQ-Bench Creative Writing	595	—

Frequently asked questions

Is Llama 3.2 3B better than Nova 2 Lite?

Which is cheaper, Llama 3.2 3B or Nova 2 Lite?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.

Is Llama 3.2 3B or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

Nova 2 Lite does, with 1M tokens against 131K.

How many benchmarks do Llama 3.2 3B and Nova 2 Lite share?

14 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Nova 2 Lite has 19.