Model comparison

Granite 4.2 8B vs MiniMax-M2

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 36.9 on the Noometry Index.

Last verified October 10, 2026. 11 shared benchmarks.

Granite 4.2 8B IBM

40.0

Rank #143 Confirmed

MiniMax-M2

MiniMax

36.9

Rank #201 Confirmed

Summary

They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 3 categories and MiniMax-M2 in 4 categories; 5 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Granite 4.2 8B leads 25.5 to 18.6.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
MiniMax-M2 accepts more context: 205K tokens versus 131K.

Side by side

Granite 4.2 8B and MiniMax-M2 specifications
	Granite 4.2 8B	MiniMax-M2
Provider	IBM	MiniMax
Noometry Index	40.0	36.9
Released	—	2025-10-27
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	21

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

Category by category

Coding Too close to call

Granite 4.2 8B: 39.9 (#138), MiniMax-M2: 39.1 (#151)

Coding benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
LMArena Coding	1379	1370
SWE-bench Verified (bash only)	—	61%
LMArena WebDev	—	1297

Agentic & Tool Use Not comparable

Granite 4.2 8B: —, MiniMax-M2: 24.9 (#102)

Agentic & Tool Use benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
Terminal-Bench	—	30%
Vending-Bench 2	—	160.6

Reasoning Granite 4.2 8B leads

Granite 4.2 8B: 25.5 (#130), MiniMax-M2: 18.6 (#256)

Reasoning benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
LMArena Hard Prompts	1327	1357
Kagi LLM Benchmark	—	57.8%
NYT Connections (extended)	—	14.8%

Math Not comparable

Granite 4.2 8B: —, MiniMax-M2: 34.6 (#158)

Math benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
LMArena Math	—	1350

Knowledge Granite 4.2 8B leads

Granite 4.2 8B: 37.7 (#144), MiniMax-M2: 36.3 (#160)

Knowledge benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
LMArena Expert	1380	1336

Multilingual MiniMax-M2 leads

Granite 4.2 8B: 44.5 (#173), MiniMax-M2: 45.6 (#165)

Multilingual benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
LMArena Non-English	1299	1314
LMArena Chinese	1361	1367
LMArena Russian	1283	1332
LMArena French	—	1336
LMArena German	—	1366
LMArena Spanish	—	1326

Instruction Following MiniMax-M2 leads

Granite 4.2 8B: 68.7 (#183), MiniMax-M2: 70.4 (#160)

Instruction Following benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
LMArena Instruction Following	1298	1329

Long Context Too close to call

Granite 4.2 8B: 40.2 (#154), MiniMax-M2: 40.5 (#148)

Long Context benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
LMArena Longer Query	1323	1332

Writing & Preference MiniMax-M2 leads

Granite 4.2 8B: 49.8 (#183), MiniMax-M2: 53.3 (#157)

Writing & Preference benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M2
LMArena Text	1319	1340
LMArena Creative Writing	1238	1288
LMArena Multi-Turn	1299	1362

Frequently asked questions

Is Granite 4.2 8B better than MiniMax-M2?

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 36.9 on the Noometry Index.

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

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

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

They score almost the same on coding (39.9 vs 39.1); test both on your own repository before choosing.

Which has the bigger context window?

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

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

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and MiniMax-M2 has 21.