Model comparison

Ministral 3B vs Mistral Small 3.1

Mistral Small 3.1 is the stronger model overall, scoring 31.4 to 25.6 on the Noometry Index. Ministral 3B costs 10× less per token, which makes it the better buy when Mistral Small 3.1's lead doesn't matter for your workload.

Last verified October 10, 2026. 2 shared benchmarks.

Ministral 3B

Mistral AI

25.6

Rank #336 Confirmed

Mistral Small 3.1

Mistral AI

31.4

Rank #263 Confirmed

Summary

They share 2 benchmarks with published results for both. Ministral 3B scores higher in 1 category and Mistral Small 3.1 in 2 categories; 3 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Mistral Small 3.1 leads 22.6 to 10.4.
The biggest single-benchmark swing is GPQA Diamond: 25.3% for Ministral 3B and 41.9% for Mistral Small 3.1.
Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.

Side by side

Ministral 3B and Mistral Small 3.1 specifications
	Ministral 3B	Mistral Small 3.1
Provider	Mistral AI	Mistral AI
Noometry Index	25.6	31.4
Released	2024-10-01	2025-03-17
Weights	Open	Open
Context window	128K	128K
Max output	128K	102K
Input $ / M tokens	$0.04	$0.35
Output $ / M tokens	$0.04	$0.56
Results tracked	6	28

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

Category by category

Coding Not comparable

Ministral 3B: —, Mistral Small 3.1: 37.7 (#175)

Coding benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
LMArena Coding	—	1309

Reasoning Mistral Small 3.1 leads

Ministral 3B: 17.7 (#278), Mistral Small 3.1: 18.9 (#249)

Reasoning benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
Epoch Capabilities Index	118.08	127.48
Chess Puzzles	—	1%
LMArena Hard Prompts	—	1278
DTBench	51.7%	—
LMCA	5.5%	—

Math Ministral 3B leads

Ministral 3B: 24.5 (#257), Mistral Small 3.1: 13.7 (#295)

Math benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
OTIS Mock AIME 2024-2025	—	3.9%
Omni-MATH	—	24.8%
LMArena Math	—	1261
MATH Level 5	14.4%	—

Knowledge Mistral Small 3.1 leads

Ministral 3B: 10.4 (#297), Mistral Small 3.1: 22.6 (#266)

Knowledge benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
GPQA Diamond	25.3%	41.9%
MMLU-Pro	—	61%
Vectara Hallucination Rate	7.3%	—
GPQA (HELM)	—	39.2%
LMArena Expert	—	1258

Multimodal Not comparable

Ministral 3B: —, Mistral Small 3.1: 32.6 (#93)

Multimodal benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
LMArena Vision	—	1136

Multilingual Not comparable

Ministral 3B: —, Mistral Small 3.1: 41.4 (#204)

Multilingual benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
LMArena Non-English	—	1255
LMArena Chinese	—	1254
LMArena French	—	1270
LMArena German	—	1266
LMArena Japanese	—	1210
LMArena Korean	—	1206
LMArena Russian	—	1263
LMArena Spanish	—	1283

Instruction Following Not comparable

Ministral 3B: —, Mistral Small 3.1: 63.8 (#225)

Instruction Following benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
IFEval	—	75%
LMArena Instruction Following	—	1264

Long Context Not comparable

Ministral 3B: —, Mistral Small 3.1: 39.5 (#172)

Long Context benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
LMArena Longer Query	—	1300

Writing & Preference Not comparable

Ministral 3B: —, Mistral Small 3.1: 37.2 (#254)

Writing & Preference benchmarks
Benchmark	Ministral 3B	Mistral Small 3.1
LMArena Text	—	1278
LMArena Creative Writing	—	1253
EQ-Bench Creative Writing	—	761
WildBench	—	78.8%
LMArena Multi-Turn	—	1270

Frequently asked questions

Is Ministral 3B better than Mistral Small 3.1?

Which is cheaper, Ministral 3B or Mistral Small 3.1?

Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.

Which has the bigger context window?

Both accept 128K tokens.

How many benchmarks do Ministral 3B and Mistral Small 3.1 share?

2 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Mistral Small 3.1 has 28.