Model comparison

Granite 4.2 8B vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 40.5 on the Noometry Index. Granite 4.2 8B costs 13× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified October 11, 2026. 11 shared benchmarks.

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

Step 5 Preview

StepFun

47.9

Rank #58 Confirmed

Summary

They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 0 categories and Step 5 Preview in 7 categories; 7 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 26.6.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
Step 5 Preview accepts more context: 1.02M tokens versus 131K.
Granite 4.2 8B has downloadable open weights; the other is API-only.

Side by side

Granite 4.2 8B and Step 5 Preview specifications
	Granite 4.2 8B	Step 5 Preview
Provider	IBM	StepFun
Noometry Index	40.5	47.9
Released	—	2026-09-16
Weights	Open	Proprietary
Context window	131K	1.02M
Max output	118K	66K
Input $ / M tokens	$0.06	$1
Output $ / M tokens	$0.25	$2.70
Results tracked	11	18

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

Category by category

Coding Step 5 Preview leads

Granite 4.2 8B: 40.5 (#137), Step 5 Preview: 51.8 (#36)

Coding benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
LMArena Coding	1380	1480
LMArena WebDev	—	1564
SciCode	—	58.9%

Reasoning Step 5 Preview leads

Granite 4.2 8B: 26.6 (#131), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
LMArena Hard Prompts	1329	1465
CritPt	—	20.9%

Math Not comparable

Granite 4.2 8B: —, Step 5 Preview: 46.1 (#72)

Math benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
ProofBench	—	42%
LMArena Math	—	1470

Knowledge Step 5 Preview leads

Granite 4.2 8B: 38.4 (#145), Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
LMArena Expert	1384	1470

Multimodal Not comparable

Granite 4.2 8B: —, Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
LMArena Vision	—	1267

Multilingual Step 5 Preview leads

Granite 4.2 8B: 44.5 (#178), Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
LMArena Non-English	1302	1432
LMArena Chinese	1366	1519
LMArena Russian	1285	1436
LMArena Spanish	—	1439

Instruction Following Step 5 Preview leads

Granite 4.2 8B: 68.7 (#184), Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
LMArena Instruction Following	1301	1444

Long Context Step 5 Preview leads

Granite 4.2 8B: 40.3 (#159), Step 5 Preview: 44.5 (#64)

Long Context benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
LMArena Longer Query	1324	1455

Writing & Preference Step 5 Preview leads

Granite 4.2 8B: 49.6 (#189), Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
Benchmark	Granite 4.2 8B	Step 5 Preview
LMArena Text	1320	1442
LMArena Creative Writing	1236	1410
LMArena Multi-Turn	1301	1447

Frequently asked questions

Is Granite 4.2 8B better than Step 5 Preview?

Which is cheaper, Granite 4.2 8B or Step 5 Preview?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is Granite 4.2 8B or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 40.5 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 131K.

How many benchmarks do Granite 4.2 8B and Step 5 Preview share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Step 5 Preview has 18.