Model comparison

Llama 3.2 3B vs Mercury 2

Mercury 2 is the stronger model overall, scoring 39.1 to 28.9 on the Noometry Index. Llama 3.2 3B costs 3.1× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.

Last verified October 10, 2026. 11 shared benchmarks.

Llama 3.2 3B

Summary

They share 11 benchmarks with published results for both. Llama 3.2 3B scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 24.7.
Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
Llama 3.2 3B accepts more context: 131K tokens versus 128K.
Llama 3.2 3B has downloadable open weights; the other is API-only.

Side by side

Llama 3.2 3B and Mercury 2 specifications
	Llama 3.2 3B	Mercury 2
Provider	Meta	Inception
Noometry Index	28.9	39.1
Released	2024-09-24	2026-02-20
Weights	Open	Proprietary
Context window	131K	128K
Max output	118K	50K
Input $ / M tokens	$0.05	$0.25
Output $ / M tokens	$0.33	$0.75
Results tracked	18	17

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

Category by category

Coding Mercury 2 leads

Llama 3.2 3B: 27.6 (#319), Mercury 2: 33.5 (#255)

Coding benchmarks
Benchmark	Llama 3.2 3B	Mercury 2
LMArena Coding	1098	1391
LMArena WebDev	—	1171
SciCode	—	38.7%
WeirdML	—	43.2%
BigCodeBench Instruct	23.4%	—
BigCodeBench Complete	28.3%	—
ALE-Bench	—	785.58

Agentic & Tool Use Not comparable

Llama 3.2 3B: 20.1 (#143), Mercury 2: —

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

Reasoning Mercury 2 leads

Llama 3.2 3B: 21.0 (#228), Mercury 2: 23.8 (#170)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	Mercury 2
LMArena Hard Prompts	1095	1362
CritPt	—	0.8%

Math Not comparable

Llama 3.2 3B: 32.4 (#214), Mercury 2: —

Math benchmarks
Benchmark	Llama 3.2 3B	Mercury 2
LMArena Math	1126	—

Knowledge Mercury 2 leads

Llama 3.2 3B: 29.7 (#235), Mercury 2: 36.2 (#172)

Knowledge benchmarks
Benchmark	Llama 3.2 3B	Mercury 2
LMArena Expert	1090	1358
Vectara Hallucination Rate	—	12.3%

Multilingual Mercury 2 leads

Llama 3.2 3B: 26.2 (#281), Mercury 2: 46.6 (#157)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	Mercury 2
LMArena Non-English	1019	1331
LMArena Chinese	1017	1417
LMArena Russian	949	1304
LMArena German	1056	—

Instruction Following Mercury 2 leads

Llama 3.2 3B: 56.0 (#275), Mercury 2: 70.2 (#165)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	Mercury 2
LMArena Instruction Following	1089	1329

Long Context Mercury 2 leads

Llama 3.2 3B: 33.4 (#261), Mercury 2: 40.5 (#154)

Long Context benchmarks
Benchmark	Llama 3.2 3B	Mercury 2
LMArena Longer Query	1100	1330

Writing & Preference Mercury 2 leads

Llama 3.2 3B: 24.7 (#307), Mercury 2: 53.8 (#155)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	Mercury 2
LMArena Text	1110	1355
LMArena Creative Writing	1094	1289
LMArena Multi-Turn	1105	1358
EQ-Bench Creative Writing	595	—

Frequently asked questions

Is Llama 3.2 3B better than Mercury 2?

Which is cheaper, Llama 3.2 3B or Mercury 2?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

Is Llama 3.2 3B or Mercury 2 better for coding?

Mercury 2 scores higher on coding benchmarks: 33.5 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

Llama 3.2 3B does, with 131K tokens against 128K.

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

11 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Mercury 2 has 17.