Model comparison

Llama 3.2 1B vs Mercury 2.5

Mercury 2.5 is the stronger model overall, scoring 33.5 to 20.1 on the Noometry Index.

Last verified October 12, 2026. 0 shared benchmarks.

Summary

The widest gap is in coding, where Mercury 2.5 leads 39.5 to 21.1.
Both cost about the same: $0.027 input and $0.20 output per million tokens.
Mercury 2.5 accepts more context: 260K tokens versus 60K.
Llama 3.2 1B has downloadable open weights; the other is API-only.

Side by side

Llama 3.2 1B and Mercury 2.5 specifications
	Llama 3.2 1B	Mercury 2.5
Provider	Meta	Inception
Noometry Index	20.1	33.5
Released	2024-09-24	2026-09-08
Weights	Open	Proprietary
Context window	60K	260K
Max output	54K	66K
Input $ / M tokens	$0.027	$0.04
Output $ / M tokens	$0.20	$0.15
Results tracked	22	4

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

Category by category

Coding Mercury 2.5 leads

Llama 3.2 1B: 21.1 (#338), Mercury 2.5: 39.5 (#156)

Coding benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
SciCode	—	38.5%
BigCodeBench Instruct	8.2%	—
LMArena Coding	1070	—
BigCodeBench Complete	11.3%	—
ALE-Bench	—	301.65

Agentic & Tool Use Not comparable

Llama 3.2 1B: 14.6 (#150), Mercury 2.5: —

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
Berkeley Function Calling Leaderboard	10.8%	—
BALROG	6.6%	—

Reasoning Mercury 2.5 leads

Llama 3.2 1B: 16.2 (#308), Mercury 2.5: 22.4 (#193)

Reasoning benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
CritPt	—	0%
Chess Puzzles	0%	—
LMArena Hard Prompts	1044	—
Epoch Capabilities Index	101.99	—

Math Mercury 2.5 leads

Llama 3.2 1B: 10.4 (#313), Mercury 2.5: 23.3 (#272)

Math benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
OTIS Mock AIME 2024-2025	0.6%	—
ProofBench	—	3%
LMArena Math	1086	—

Knowledge Not comparable

Llama 3.2 1B: 7.2 (#312), Mercury 2.5: —

Knowledge benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
GPQA Diamond	23.9%	—
LMArena Expert	1007	—

Multilingual Not comparable

Llama 3.2 1B: 23.8 (#292), Mercury 2.5: —

Multilingual benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
LMArena Non-English	973	—
LMArena Chinese	959	—
LMArena German	1014	—
LMArena Russian	941	—

Instruction Following Not comparable

Llama 3.2 1B: 52.4 (#290), Mercury 2.5: —

Instruction Following benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
LMArena Instruction Following	1031	—

Long Context Not comparable

Llama 3.2 1B: 31.9 (#274), Mercury 2.5: —

Long Context benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
LMArena Longer Query	1050	—

Writing & Preference Not comparable

Llama 3.2 1B: 21.3 (#310), Mercury 2.5: —

Writing & Preference benchmarks
Benchmark	Llama 3.2 1B	Mercury 2.5
LMArena Text	1055	—
LMArena Creative Writing	1033	—
EQ-Bench Creative Writing	200	—
LMArena Multi-Turn	1030	—

Frequently asked questions

Is Llama 3.2 1B better than Mercury 2.5?

Mercury 2.5 is the stronger model overall, scoring 33.5 to 20.1 on the Noometry Index.

Which is cheaper, Llama 3.2 1B or Mercury 2.5?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Llama 3.2 1B lists at $0.027 and $0.20.

Is Llama 3.2 1B or Mercury 2.5 better for coding?

Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 21.1 in the Noometry coding category.

Which has the bigger context window?

Mercury 2.5 does, with 260K tokens against 60K.

How many benchmarks do Llama 3.2 1B and Mercury 2.5 share?

0 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Mercury 2.5 has 4.