Model comparison

Granite 4.2 8B vs Hy3

Hy3 is the stronger model overall, scoring 44.2 to 40.5 on the Noometry Index.

Last verified October 10, 2026. 11 shared benchmarks.

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

Hy3

Tencent

44.2

Rank #79 Confirmed

Summary

They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 1 category and Hy3 in 6 categories; 6 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Hy3 leads 62.2 to 49.6.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.0825 / $0.33 for Hy3.
Hy3 accepts more context: 262K tokens versus 131K.

Side by side

Granite 4.2 8B and Hy3 specifications
	Granite 4.2 8B	Hy3
Provider	IBM	Tencent
Noometry Index	40.5	44.2
Released	—	2026-07-06
Weights	Open	Open
Context window	131K	262K
Max output	118K	128K
Input $ / M tokens	$0.06	$0.0825
Output $ / M tokens	$0.25	$0.33
Results tracked	11	19

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

Category by category

Coding Hy3 leads

Granite 4.2 8B: 40.5 (#137), Hy3: 46.8 (#63)

Coding benchmarks
Benchmark	Granite 4.2 8B	Hy3
LMArena Coding	1380	1464
LMArena WebDev	—	1508

Reasoning Too close to call

Granite 4.2 8B: 26.6 (#131), Hy3: 26.1 (#136)

Reasoning benchmarks
Benchmark	Granite 4.2 8B	Hy3
LMArena Hard Prompts	1329	1447
NYT Connections (extended)	—	41.2%

Math Not comparable

Granite 4.2 8B: —, Hy3: 40.1 (#93)

Math benchmarks
Benchmark	Granite 4.2 8B	Hy3
LMArena Math	—	1475

Knowledge Hy3 leads

Granite 4.2 8B: 38.4 (#145), Hy3: 40.8 (#114)

Knowledge benchmarks
Benchmark	Granite 4.2 8B	Hy3
LMArena Expert	1384	1460

Multilingual Hy3 leads

Granite 4.2 8B: 44.5 (#178), Hy3: 53.5 (#65)

Multilingual benchmarks
Benchmark	Granite 4.2 8B	Hy3
LMArena Non-English	1302	1426
LMArena Chinese	1366	1493
LMArena Russian	1285	1432
LMArena French	—	1461
LMArena German	—	1439
LMArena Japanese	—	1392
LMArena Korean	—	1395
LMArena Spanish	—	1456

Instruction Following Hy3 leads

Granite 4.2 8B: 68.7 (#184), Hy3: 75.1 (#70)

Instruction Following benchmarks
Benchmark	Granite 4.2 8B	Hy3
LMArena Instruction Following	1301	1426

Long Context Hy3 leads

Granite 4.2 8B: 40.3 (#159), Hy3: 44.1 (#75)

Long Context benchmarks
Benchmark	Granite 4.2 8B	Hy3
LMArena Longer Query	1324	1442

Writing & Preference Hy3 leads

Granite 4.2 8B: 49.6 (#189), Hy3: 62.2 (#81)

Writing & Preference benchmarks
Benchmark	Granite 4.2 8B	Hy3
LMArena Text	1320	1439
LMArena Creative Writing	1236	1402
LMArena Multi-Turn	1301	1436

Frequently asked questions

Is Granite 4.2 8B better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 40.5 on the Noometry Index.

Which is cheaper, Granite 4.2 8B or Hy3?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Hy3 lists at $0.0825 and $0.33.

Is Granite 4.2 8B or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 40.5 in the Noometry coding category.

Which has the bigger context window?

Hy3 does, with 262K tokens against 131K.

How many benchmarks do Granite 4.2 8B and Hy3 share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Hy3 has 19.