Model comparison

Ministral 8B vs Mistral Medium 3.5

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 27.8 on the Noometry Index. Ministral 8B costs 30× 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. 12 shared benchmarks.

Ministral 8B

Mistral AI

27.8

Rank #321 Confirmed

Mistral Medium 3.5

Mistral AI

39.6

Rank #151 Confirmed

Summary

They share 12 benchmarks with published results for both. Ministral 8B scores higher in 1 category and Mistral Medium 3.5 in 7 categories; 8 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Mistral Medium 3.5 leads 39.3 to 12.5.
Ministral 8B is cheaper at $0.10 / $0.10 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 128K.

Side by side

Ministral 8B and Mistral Medium 3.5 specifications
	Ministral 8B	Mistral Medium 3.5
Provider	Mistral AI	Mistral AI
Noometry Index	27.8	39.6
Released	2024-10-01	—
Weights	Open	Open
Context window	128K	262K
Max output	128K	210K
Input $ / M tokens	$0.10	$1.50
Output $ / M tokens	$0.10	$7.50
Results tracked	17	22

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

Category by category

Coding Mistral Medium 3.5 leads

Ministral 8B: 34.4 (#226), Mistral Medium 3.5: 35.7 (#208)

Coding benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Coding	1202	1461
LMArena WebDev	—	1263

Agentic & Tool Use Not comparable

Ministral 8B: 16.2 (#140), Mistral Medium 3.5: —

Agentic & Tool Use benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
Berkeley Function Calling Leaderboard	11.1%	—

Reasoning Ministral 8B leads

Ministral 8B: 17.7 (#279), Mistral Medium 3.5: 16.6 (#290)

Reasoning benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Hard Prompts	1191	1436
Kagi LLM Benchmark	—	41.4%
NYT Connections (extended)	—	12.9%
DTBench	45.7%	—
Epoch Capabilities Index	—	141.42

Math Mistral Medium 3.5 leads

Ministral 8B: 23.7 (#262), Mistral Medium 3.5: 36.4 (#113)

Math benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Math	1188	1432
MATH Level 5	14.9%	—

Knowledge Mistral Medium 3.5 leads

Ministral 8B: 12.5 (#292), Mistral Medium 3.5: 39.3 (#123)

Knowledge benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Expert	1170	1431
GPQA Diamond	27.1%	—
Vectara Hallucination Rate	7.4%	—

Multimodal Not comparable

Ministral 8B: —, Mistral Medium 3.5: 37.6 (#64)

Multimodal benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Vision	—	1222

Multilingual Mistral Medium 3.5 leads

Ministral 8B: 35.3 (#242), Mistral Medium 3.5: 52.1 (#93)

Multilingual benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Non-English	1165	1405
LMArena Chinese	1193	1443
LMArena Russian	1195	1396
LMArena French	—	1448
LMArena German	—	1453
LMArena Korean	—	1387
LMArena Spanish	—	1406

Instruction Following Mistral Medium 3.5 leads

Ministral 8B: 60.7 (#245), Mistral Medium 3.5: 74.7 (#87)

Instruction Following benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Instruction Following	1161	1414

Long Context Mistral Medium 3.5 leads

Ministral 8B: 36.7 (#222), Mistral Medium 3.5: 43.2 (#101)

Long Context benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Longer Query	1212	1414

Writing & Preference Mistral Medium 3.5 leads

Ministral 8B: 39.8 (#241), Mistral Medium 3.5: 58.6 (#113)

Writing & Preference benchmarks
Benchmark	Ministral 8B	Mistral Medium 3.5
LMArena Text	1191	1421
LMArena Creative Writing	1175	1372
LMArena Multi-Turn	1166	1423
EQ-Bench 4	—	993

Frequently asked questions

Is Ministral 8B better than Mistral Medium 3.5?

Which is cheaper, Ministral 8B or Mistral Medium 3.5?

Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Ministral 8B or Mistral Medium 3.5 better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 128K.

How many benchmarks do Ministral 8B and Mistral Medium 3.5 share?

12 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Mistral Medium 3.5 has 22.