Model comparison

Magistral Medium vs MiniMax-M2.1

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 35.2 on the Noometry Index.

Last verified October 11, 2026. 17 shared benchmarks.

Magistral Medium

Mistral AI

35.2

Rank #227 Confirmed

MiniMax-M2.1

MiniMax

38.9

Rank #178 Confirmed

Summary

They share 17 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and MiniMax-M2.1 in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 46.3.
MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $5 for Magistral Medium.
Magistral Medium accepts more context: 262K tokens versus 205K.

Side by side

Magistral Medium and MiniMax-M2.1 specifications
	Magistral Medium	MiniMax-M2.1
Provider	Mistral AI	MiniMax
Noometry Index	35.2	38.9
Released	2025-03-17	2025-12-23
Weights	Open	Open
Context window	262K	205K
Max output	16K	131K
Input $ / M tokens	$2	$0.30
Output $ / M tokens	$5	$1.20
Results tracked	22	22

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

Category by category

Coding MiniMax-M2.1 leads

Magistral Medium: 39.1 (#161), MiniMax-M2.1: 40.4 (#143)

Coding benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
LMArena Coding	1319	1421
LMArena WebDev	—	1384
SciCode	39.2%	—
ALE-Bench	—	623.83

Agentic & Tool Use Not comparable

Magistral Medium: —, MiniMax-M2.1: 27.9 (#98)

Agentic & Tool Use benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
Terminal-Bench	—	36.6%

Reasoning MiniMax-M2.1 leads

Magistral Medium: 8.6 (#348), MiniMax-M2.1: 16.6 (#302)

Reasoning benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
LMArena Hard Prompts	1267	1411
ARC-AGI-2	0%	—
Kagi LLM Benchmark	16.2%	—
NYT Connections (extended)	—	11.2%
ARC-AGI-1	6.1%	—
CritPt	0.3%	—

Math MiniMax-M2.1 leads

Magistral Medium: 35.1 (#189), MiniMax-M2.1: 38.3 (#138)

Math benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
LMArena Math	1250	1397

Knowledge MiniMax-M2.1 leads

Magistral Medium: 33.5 (#202), MiniMax-M2.1: 38.3 (#147)

Knowledge benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
LMArena Expert	1223	1431
Vectara Hallucination Rate	—	11.8%

Multilingual MiniMax-M2.1 leads

Magistral Medium: 39.6 (#224), MiniMax-M2.1: 50.0 (#128)

Multilingual benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
LMArena Non-English	1232	1378
LMArena Chinese	1227	1430
LMArena French	1267	1404
LMArena German	1248	1381
LMArena Japanese	1175	1287
LMArena Korean	1125	1298
LMArena Russian	1224	1387
LMArena Spanish	1271	1397

Instruction Following MiniMax-M2.1 leads

Magistral Medium: 66.0 (#211), MiniMax-M2.1: 73.8 (#112)

Instruction Following benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
LMArena Instruction Following	1254	1400

Long Context MiniMax-M2.1 leads

Magistral Medium: 39.3 (#183), MiniMax-M2.1: 43.2 (#101)

Long Context benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
LMArena Longer Query	1295	1416

Writing & Preference MiniMax-M2.1 leads

Magistral Medium: 46.3 (#219), MiniMax-M2.1: 58.3 (#120)

Writing & Preference benchmarks
Benchmark	Magistral Medium	MiniMax-M2.1
LMArena Text	1255	1392
LMArena Creative Writing	1245	1361
LMArena Multi-Turn	1275	1396

Frequently asked questions

Is Magistral Medium better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 35.2 on the Noometry Index.

Which is cheaper, Magistral Medium or MiniMax-M2.1?

MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Magistral Medium lists at $2 and $5.

Is Magistral Medium or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

Magistral Medium does, with 262K tokens against 205K.

How many benchmarks do Magistral Medium and MiniMax-M2.1 share?

17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and MiniMax-M2.1 has 22.