Model comparison

Mistral Medium 3.5 vs Mistral Small 3

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 31.2 on the Noometry Index. Mistral Small 3 costs 52× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

Last verified October 10, 2026. 16 shared benchmarks.

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Mistral Small 3

Mistral AI

31.2

Rank #278 Confirmed

Summary

They share 16 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 6 categories and Mistral Small 3 in 2 categories; 7 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.5 to 32.2.
Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
Mistral Medium 3.5 accepts more context: 262K tokens versus 33K.

Side by side

Mistral Medium 3.5 and Mistral Small 3 specifications
	Mistral Medium 3.5	Mistral Small 3
Provider	Mistral AI	Mistral AI
Noometry Index	40.2	31.2
Released	—	2025-01-30
Weights	Open	Open
Context window	262K	33K
Max output	210K	16K
Input $ / M tokens	$1.50	$0.05
Output $ / M tokens	$7.50	$0.08
Results tracked	22	24

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

Category by category

Coding Too close to call

Mistral Medium 3.5: 36.0 (#213), Mistral Small 3: 36.5 (#207)

Coding benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Coding	1461	1246
LMArena WebDev	1264	—
BigCodeBench Instruct	—	45.3%
BigCodeBench Complete	—	50.4%

Reasoning Mistral Small 3 leads

Mistral Medium 3.5: 17.3 (#295), Mistral Small 3: 18.9 (#273)

Reasoning benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Hard Prompts	1436	1233
Epoch Capabilities Index	141.35	127.07
Kagi LLM Benchmark	41.4%	—
NYT Connections (extended)	12.9%	—
Chess Puzzles	—	0%

Math Mistral Medium 3.5 leads

Mistral Medium 3.5: 39.1 (#113), Mistral Small 3: 16.3 (#295)

Math benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Math	1431	1240
OTIS Mock AIME 2024-2025	—	6.7%

Knowledge Mistral Medium 3.5 leads

Mistral Medium 3.5: 40.0 (#126), Mistral Small 3: 25.1 (#263)

Knowledge benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Expert	1432	1202
GPQA Diamond	—	47.3%
Confabulations	—	25.2%

Multimodal Not comparable

Mistral Medium 3.5: 38.3 (#65), Mistral Small 3: —

Multimodal benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Vision	1223	—

Multilingual Mistral Medium 3.5 leads

Mistral Medium 3.5: 51.9 (#100), Mistral Small 3: 37.3 (#236)

Multilingual benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Non-English	1404	1198
LMArena Chinese	1442	1204
LMArena French	1448	1203
LMArena German	1451	1211
LMArena Korean	1385	1188
LMArena Russian	1395	1216
LMArena Japanese	—	1111
LMArena Spanish	1409	—

Instruction Following Mistral Medium 3.5 leads

Mistral Medium 3.5: 74.6 (#90), Mistral Small 3: 63.7 (#229)

Instruction Following benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Instruction Following	1415	1214

Long Context Mistral Medium 3.5 leads

Mistral Medium 3.5: 43.2 (#103), Mistral Small 3: 37.8 (#211)

Long Context benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Longer Query	1415	1246

Writing & Preference Mistral Medium 3.5 leads

Mistral Medium 3.5: 58.5 (#117), Mistral Small 3: 32.2 (#280)

Writing & Preference benchmarks
Benchmark	Mistral Medium 3.5	Mistral Small 3
LMArena Text	1421	1234
LMArena Creative Writing	1374	1195
LMArena Multi-Turn	1423	1217
EQ-Bench Creative Writing	—	707
EQ-Bench 4	993	—

Frequently asked questions

Is Mistral Medium 3.5 better than Mistral Small 3?

Which is cheaper, Mistral Medium 3.5 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; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Mistral Medium 3.5 or Mistral Small 3 better for coding?

They score almost the same on coding (36.0 vs 36.5); test both on your own repository before choosing.

Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 33K.

How many benchmarks do Mistral Medium 3.5 and Mistral Small 3 share?

16 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Mistral Small 3 has 24.