Model comparison

Llama 3.2 3B vs Mistral Small 3

Mistral Small 3 is the stronger model overall, scoring 31.2 to 28.9 on the Noometry Index.

Last verified October 11, 2026. 16 shared benchmarks.

Summary

They share 16 benchmarks with published results for both. Llama 3.2 3B scores higher in 3 categories and Mistral Small 3 in 5 categories; 8 gaps are clear of the uncertainty.
The widest gap is in math, where Llama 3.2 3B leads 32.4 to 16.3.
The biggest single-benchmark swing is BigCodeBench Complete: 28.3% for Llama 3.2 3B and 50.4% for Mistral Small 3.
Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.
Llama 3.2 3B accepts more context: 131K tokens versus 33K.

Side by side

Llama 3.2 3B and Mistral Small 3 specifications
	Llama 3.2 3B	Mistral Small 3
Provider	Meta	Mistral AI
Noometry Index	28.9	31.2
Released	2024-09-24	2025-01-30
Weights	Open	Open
Context window	131K	33K
Max output	118K	16K
Input $ / M tokens	$0.05	$0.05
Output $ / M tokens	$0.33	$0.08
Results tracked	18	24

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

Category by category

Coding Mistral Small 3 leads

Llama 3.2 3B: 27.6 (#319), Mistral Small 3: 36.5 (#207)

Coding benchmarks
Benchmark	Llama 3.2 3B	Mistral Small 3
BigCodeBench Instruct	23.4%	45.3%
LMArena Coding	1098	1246
BigCodeBench Complete	28.3%	50.4%

Agentic & Tool Use Not comparable

Llama 3.2 3B: 20.1 (#143), Mistral Small 3: —

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

Reasoning Llama 3.2 3B leads

Llama 3.2 3B: 21.0 (#228), Mistral Small 3: 18.9 (#273)

Reasoning benchmarks
Benchmark	Llama 3.2 3B	Mistral Small 3
LMArena Hard Prompts	1095	1233
Chess Puzzles	—	0%
Epoch Capabilities Index	—	127.07

Math Llama 3.2 3B leads

Llama 3.2 3B: 32.4 (#214), Mistral Small 3: 16.3 (#295)

Math benchmarks
Benchmark	Llama 3.2 3B	Mistral Small 3
LMArena Math	1126	1240
OTIS Mock AIME 2024-2025	—	6.7%

Knowledge Llama 3.2 3B leads

Llama 3.2 3B: 29.7 (#235), Mistral Small 3: 25.1 (#263)

Knowledge benchmarks
Benchmark	Llama 3.2 3B	Mistral Small 3
LMArena Expert	1090	1202
GPQA Diamond	—	47.3%
Confabulations	—	25.2%

Multilingual Mistral Small 3 leads

Llama 3.2 3B: 26.2 (#281), Mistral Small 3: 37.3 (#236)

Multilingual benchmarks
Benchmark	Llama 3.2 3B	Mistral Small 3
LMArena Non-English	1019	1198
LMArena Chinese	1017	1204
LMArena German	1056	1211
LMArena Russian	949	1216
LMArena French	—	1203
LMArena Japanese	—	1111
LMArena Korean	—	1188

Instruction Following Mistral Small 3 leads

Llama 3.2 3B: 56.0 (#275), Mistral Small 3: 63.7 (#229)

Instruction Following benchmarks
Benchmark	Llama 3.2 3B	Mistral Small 3
LMArena Instruction Following	1089	1214

Long Context Mistral Small 3 leads

Llama 3.2 3B: 33.4 (#261), Mistral Small 3: 37.8 (#211)

Long Context benchmarks
Benchmark	Llama 3.2 3B	Mistral Small 3
LMArena Longer Query	1100	1246

Writing & Preference Mistral Small 3 leads

Llama 3.2 3B: 24.7 (#307), Mistral Small 3: 32.2 (#280)

Writing & Preference benchmarks
Benchmark	Llama 3.2 3B	Mistral Small 3
LMArena Text	1110	1234
LMArena Creative Writing	1094	1195
EQ-Bench Creative Writing	595	707
LMArena Multi-Turn	1105	1217

Frequently asked questions

Is Llama 3.2 3B better than Mistral Small 3?

Mistral Small 3 is the stronger model overall, scoring 31.2 to 28.9 on the Noometry Index.

Which is cheaper, Llama 3.2 3B or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.

Is Llama 3.2 3B or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

Llama 3.2 3B does, with 131K tokens against 33K.

How many benchmarks do Llama 3.2 3B and Mistral Small 3 share?

16 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Mistral Small 3 has 24.