Model comparison

MiniMax-M2 vs Mistral Medium 3.5

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 37.4 on the Noometry Index. MiniMax-M2 costs 5.7× 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. 18 shared benchmarks.

MiniMax-M2

MiniMax

37.4

Rank #204 Confirmed

Mistral Medium 3.5

Mistral AI

40.2

Rank #152 Confirmed

Summary

They share 18 benchmarks with published results for both. MiniMax-M2 scores higher in 2 categories and Mistral Medium 3.5 in 6 categories; 8 gaps are clear of the uncertainty.
The widest gap is in multilingual, where Mistral Medium 3.5 leads 51.9 to 45.3.
The biggest single-benchmark swing is Kagi LLM Benchmark: 57.8% for MiniMax-M2 and 41.4% for Mistral Medium 3.5.
MiniMax-M2 is cheaper at $0.30 / $1.20 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 205K.

Side by side

MiniMax-M2 and Mistral Medium 3.5 specifications
	MiniMax-M2	Mistral Medium 3.5
Provider	MiniMax	Mistral AI
Noometry Index	37.4	40.2
Released	2025-10-27	—
Weights	Open	Open
Context window	205K	262K
Max output	131K	210K
Input $ / M tokens	$0.30	$1.50
Output $ / M tokens	$1.20	$7.50
Results tracked	21	22

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

Category by category

Coding MiniMax-M2 leads

MiniMax-M2: 39.3 (#159), Mistral Medium 3.5: 36.0 (#213)

Coding benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
LMArena WebDev	1297	1264
LMArena Coding	1370	1461
SWE-bench Verified (bash only)	61%	—

Agentic & Tool Use Not comparable

MiniMax-M2: 25.1 (#109), Mistral Medium 3.5: —

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
Terminal-Bench	30%	—
Vending-Bench 2	160.6	—

Reasoning MiniMax-M2 leads

MiniMax-M2: 19.4 (#258), Mistral Medium 3.5: 17.3 (#295)

Reasoning benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
Kagi LLM Benchmark	57.8%	41.4%
NYT Connections (extended)	14.8%	12.9%
LMArena Hard Prompts	1357	1436
Epoch Capabilities Index	—	141.35

Math Mistral Medium 3.5 leads

MiniMax-M2: 37.3 (#160), Mistral Medium 3.5: 39.1 (#113)

Math benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
LMArena Math	1352	1431

Knowledge Mistral Medium 3.5 leads

MiniMax-M2: 37.0 (#163), Mistral Medium 3.5: 40.0 (#126)

Knowledge benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
LMArena Expert	1337	1432

Multimodal Not comparable

MiniMax-M2: —, Mistral Medium 3.5: 38.3 (#65)

Multimodal benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
LMArena Vision	—	1223

Multilingual Mistral Medium 3.5 leads

MiniMax-M2: 45.3 (#171), Mistral Medium 3.5: 51.9 (#100)

Multilingual benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
LMArena Non-English	1313	1404
LMArena Chinese	1366	1442
LMArena French	1335	1448
LMArena German	1355	1451
LMArena Russian	1331	1395
LMArena Spanish	1326	1409
LMArena Korean	—	1385

Instruction Following Mistral Medium 3.5 leads

MiniMax-M2: 70.2 (#166), Mistral Medium 3.5: 74.6 (#90)

Instruction Following benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
LMArena Instruction Following	1328	1415

Long Context Mistral Medium 3.5 leads

MiniMax-M2: 40.5 (#153), Mistral Medium 3.5: 43.2 (#103)

Long Context benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
LMArena Longer Query	1331	1415

Writing & Preference Mistral Medium 3.5 leads

MiniMax-M2: 53.0 (#162), Mistral Medium 3.5: 58.5 (#117)

Writing & Preference benchmarks
Benchmark	MiniMax-M2	Mistral Medium 3.5
LMArena Text	1340	1421
LMArena Creative Writing	1286	1374
LMArena Multi-Turn	1361	1423
EQ-Bench 4	—	993

Frequently asked questions

Is MiniMax-M2 better than Mistral Medium 3.5?

Which is cheaper, MiniMax-M2 or Mistral Medium 3.5?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is MiniMax-M2 or Mistral Medium 3.5 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 36.0 in the Noometry coding category.

Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 205K.

How many benchmarks do MiniMax-M2 and Mistral Medium 3.5 share?

18 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Mistral Medium 3.5 has 22.