Model comparison

Granite 4.2 8B vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.8 to 40.5 on the Noometry Index. Granite 4.2 8B costs 4.9× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.

Last verified October 12, 2026. 11 shared benchmarks.

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

MiniMax-M3

MiniMax

43.8

Rank #85 Confirmed

Summary

They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 0 categories and MiniMax-M3 in 7 categories; 7 gaps are clear of the uncertainty.
The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 38.4.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
MiniMax-M3 accepts more context: 1M tokens versus 131K.

Side by side

Granite 4.2 8B and MiniMax-M3 specifications
	Granite 4.2 8B	MiniMax-M3
Provider	IBM	MiniMax
Noometry Index	40.5	43.8
Released	—	2026-06-01
Weights	Open	Open
Context window	131K	1M
Max output	118K	512K
Input $ / M tokens	$0.06	$0.30
Output $ / M tokens	$0.25	$1.20
Results tracked	11	41

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

Category by category

Coding MiniMax-M3 leads

Granite 4.2 8B: 40.5 (#137), MiniMax-M3: 41.8 (#118)

Coding benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
LMArena Coding	1380	1469
FrontierCode	—	14.7%
LMArena WebDev	—	1482
SciCode	—	47.1%
ALE-Bench	—	640.02

Agentic & Tool Use Not comparable

Granite 4.2 8B: —, MiniMax-M3: 22.6 (#130)

Agentic & Tool Use benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
APEX-Agents	—	37.7%
OSWorld 2.0	—	4.6%
GBAEval	—	0.9%
Vending-Bench 2	—	2,158

Reasoning MiniMax-M3 leads

Granite 4.2 8B: 26.6 (#131), MiniMax-M3: 30.1 (#87)

Reasoning benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
LMArena Hard Prompts	1329	1447
SimpleBench	—	45.8%
NYT Connections (extended)	—	65.1%
CritPt	—	3.7%
Chess Puzzles	—	14%
Mystery Game Puzzles	—	8%
DTBench	—	78.9%
LMCA	—	33.7%
Surface Evolver Bench	—	55%
Epoch Capabilities Index	—	146.95
ForecastBench	—	61.4

Math Not comparable

Granite 4.2 8B: —, MiniMax-M3: 40.0 (#95)

Math benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
OTIS Mock AIME 2024-2025	—	71.1%
ProofBench	—	18%
LMArena Math	—	1429

Knowledge MiniMax-M3 leads

Granite 4.2 8B: 38.4 (#145), MiniMax-M3: 58.4 (#35)

Knowledge benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
LMArena Expert	1384	1461
GPQA Diamond	—	90.9%

Multimodal Not comparable

Granite 4.2 8B: —, MiniMax-M3: 40.2 (#51)

Multimodal benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
LMArena Vision	—	1253
LMArena Document	—	1435

Multilingual MiniMax-M3 leads

Granite 4.2 8B: 44.5 (#178), MiniMax-M3: 53.0 (#75)

Multilingual benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
LMArena Non-English	1302	1420
LMArena Chinese	1366	1463
LMArena Russian	1285	1428
LMArena French	—	1447
LMArena German	—	1426
LMArena Japanese	—	1381
LMArena Korean	—	1372
LMArena Spanish	—	1432

Instruction Following MiniMax-M3 leads

Granite 4.2 8B: 68.7 (#184), MiniMax-M3: 75.5 (#62)

Instruction Following benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
LMArena Instruction Following	1301	1433

Long Context MiniMax-M3 leads

Granite 4.2 8B: 40.3 (#159), MiniMax-M3: 44.2 (#72)

Long Context benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
LMArena Longer Query	1324	1445

Writing & Preference MiniMax-M3 leads

Granite 4.2 8B: 49.6 (#189), MiniMax-M3: 62.1 (#83)

Writing & Preference benchmarks
Benchmark	Granite 4.2 8B	MiniMax-M3
LMArena Text	1320	1433
LMArena Creative Writing	1236	1404
LMArena Multi-Turn	1301	1442
EQ-Bench 4	—	1150

Frequently asked questions

Is Granite 4.2 8B better than MiniMax-M3?

Which is cheaper, Granite 4.2 8B or MiniMax-M3?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

Is Granite 4.2 8B or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 40.5 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 131K.

How many benchmarks do Granite 4.2 8B and MiniMax-M3 share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and MiniMax-M3 has 41.