Model comparison

Granite 4.2 8B vs MiniMax-M2.1

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 38.9 on the Noometry Index.

Last verified October 10, 2026. 11 shared benchmarks.

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

MiniMax-M2.1

MiniMax

38.9

Rank #178 Confirmed

Summary

They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 3 categories and MiniMax-M2.1 in 4 categories; 5 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Granite 4.2 8B leads 26.6 to 16.6.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
MiniMax-M2.1 accepts more context: 205K tokens versus 131K.

Side by side

Granite 4.2 8B and MiniMax-M2.1 specifications
	Granite 4.2 8B	MiniMax-M2.1
Provider	IBM	MiniMax
Noometry Index	40.5	38.9
Released	—	2025-12-23
Weights	Open	Open
Context window	131K	205K
Max output	118K	131K
Input $ / M tokens	$0.06	$0.30
Output $ / M tokens	$0.25	$1.20
Results tracked	11	22

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

Category by category

Coding Too close to call

Granite 4.2 8B: 40.5 (#137), MiniMax-M2.1: 40.4 (#143)

Coding benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
LMArena Coding	1380	1421
LMArena WebDev	—	1384
ALE-Bench	—	623.83

Agentic & Tool Use Not comparable

Granite 4.2 8B: —, MiniMax-M2.1: 27.9 (#98)

Agentic & Tool Use benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
Terminal-Bench	—	36.6%

Reasoning Granite 4.2 8B leads

Granite 4.2 8B: 26.6 (#131), MiniMax-M2.1: 16.6 (#302)

Reasoning benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
LMArena Hard Prompts	1329	1411
NYT Connections (extended)	—	11.2%

Math Not comparable

Granite 4.2 8B: —, MiniMax-M2.1: 38.3 (#138)

Math benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
LMArena Math	—	1397

Knowledge Too close to call

Granite 4.2 8B: 38.4 (#145), MiniMax-M2.1: 38.3 (#147)

Knowledge benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
LMArena Expert	1384	1431
Vectara Hallucination Rate	—	11.8%

Multilingual MiniMax-M2.1 leads

Granite 4.2 8B: 44.5 (#178), MiniMax-M2.1: 50.0 (#128)

Multilingual benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
LMArena Non-English	1302	1378
LMArena Chinese	1366	1430
LMArena Russian	1285	1387
LMArena French	—	1404
LMArena German	—	1381
LMArena Japanese	—	1287
LMArena Korean	—	1298
LMArena Spanish	—	1397

Instruction Following MiniMax-M2.1 leads

Granite 4.2 8B: 68.7 (#184), MiniMax-M2.1: 73.8 (#112)

Instruction Following benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
LMArena Instruction Following	1301	1400

Long Context MiniMax-M2.1 leads

Granite 4.2 8B: 40.3 (#159), MiniMax-M2.1: 43.2 (#101)

Long Context benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
LMArena Longer Query	1324	1416

Writing & Preference MiniMax-M2.1 leads

Granite 4.2 8B: 49.6 (#189), MiniMax-M2.1: 58.3 (#120)

Writing & Preference benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2.1
LMArena Text	1320	1392
LMArena Creative Writing	1236	1361
LMArena Multi-Turn	1301	1396

Frequently asked questions

Is Granite 4.2 8B better than MiniMax-M2.1?

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 38.9 on the Noometry Index.

Which is cheaper, Granite 4.2 8B or MiniMax-M2.1?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

Is Granite 4.2 8B or MiniMax-M2.1 better for coding?

They score almost the same on coding (40.5 vs 40.4); test both on your own repository before choosing.

Which has the bigger context window?

MiniMax-M2.1 does, with 205K tokens against 131K.

How many benchmarks do Granite 4.2 8B and MiniMax-M2.1 share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and MiniMax-M2.1 has 22.