Model comparison

MiniMax M1 vs Mistral Small 3

MiniMax M1 is the stronger model overall, scoring 39.7 to 30.9 on the Noometry Index. Mistral Small 3 costs 15× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.

Last verified October 10, 2026. 16 shared benchmarks.

MiniMax M1

MiniMax

39.7

Rank #146 Confirmed

Mistral Small 3

Mistral AI

30.9

Rank #268 Confirmed

Summary

They share 16 benchmarks with published results for both. MiniMax M1 scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where MiniMax M1 leads 53.3 to 32.4.
Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.40 / $2.20 for MiniMax M1.
MiniMax M1 accepts more context: 1M tokens versus 33K.

Side by side

MiniMax M1 and Mistral Small 3 specifications
	MiniMax M1	Mistral Small 3
Provider	MiniMax	Mistral AI
Noometry Index	39.7	30.9
Released	2025-06-13	2025-01-30
Weights	Open	Open
Context window	1M	33K
Max output	40K	16K
Input $ / M tokens	$0.40	$0.05
Output $ / M tokens	$2.20	$0.08
Results tracked	18	24

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

Category by category

Coding MiniMax M1 leads

MiniMax M1: 39.2 (#149), Mistral Small 3: 36.0 (#203)

Coding benchmarks
Benchmark	MiniMax M1	Mistral Small 3
LMArena Coding	1359	1246
BigCodeBench Instruct	—	45.3%
BigCodeBench Complete	—	50.4%

Reasoning MiniMax M1 leads

MiniMax M1: 25.8 (#125), Mistral Small 3: 18.2 (#269)

Reasoning benchmarks
Benchmark	MiniMax M1	Mistral Small 3
LMArena Hard Prompts	1340	1233
Chess Puzzles	—	0%
Epoch Capabilities Index	—	127.06

Math MiniMax M1 leads

MiniMax M1: 34.8 (#152), Mistral Small 3: 15.3 (#290)

Math benchmarks
Benchmark	MiniMax M1	Mistral Small 3
LMArena Math	1360	1240
OTIS Mock AIME 2024-2025	—	6.7%

Knowledge MiniMax M1 leads

MiniMax M1: 35.7 (#168), Mistral Small 3: 25.0 (#258)

Knowledge benchmarks
Benchmark	MiniMax M1	Mistral Small 3
LMArena Expert	1316	1202
GPQA Diamond	—	47.3%
Confabulations	—	25.2%

Multilingual MiniMax M1 leads

MiniMax M1: 46.0 (#157), Mistral Small 3: 37.5 (#231)

Multilingual benchmarks
Benchmark	MiniMax M1	Mistral Small 3
LMArena Non-English	1320	1198
LMArena Chinese	1361	1204
LMArena French	1369	1202
LMArena German	1350	1211
LMArena Japanese	1220	1111
LMArena Korean	1263	1188
LMArena Russian	1330	1216
LMArena Spanish	1354	—

Instruction Following MiniMax M1 leads

MiniMax M1: 69.5 (#169), Mistral Small 3: 63.9 (#224)

Instruction Following benchmarks
Benchmark	MiniMax M1	Mistral Small 3
LMArena Instruction Following	1312	1214

Long Context MiniMax M1 leads

MiniMax M1: 41.4 (#136), Mistral Small 3: 37.8 (#206)

Long Context benchmarks
Benchmark	MiniMax M1	Mistral Small 3
LMArena Longer Query	1326	1246
Fiction.LiveBench	69.4%	—

Writing & Preference MiniMax M1 leads

MiniMax M1: 53.3 (#155), Mistral Small 3: 32.4 (#275)

Writing & Preference benchmarks
Benchmark	MiniMax M1	Mistral Small 3
LMArena Text	1343	1234
LMArena Creative Writing	1298	1195
LMArena Multi-Turn	1335	1217
EQ-Bench Creative Writing	—	707

Frequently asked questions

Is MiniMax M1 better than Mistral Small 3?

Which is cheaper, MiniMax M1 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; MiniMax M1 lists at $0.40 and $2.20.

Is MiniMax M1 or Mistral Small 3 better for coding?

MiniMax M1 scores higher on coding benchmarks: 39.2 versus 36.0 in the Noometry coding category.

Which has the bigger context window?

MiniMax M1 does, with 1M tokens against 33K.

How many benchmarks do MiniMax M1 and Mistral Small 3 share?

16 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and Mistral Small 3 has 24.