Model comparison

Granite 4.2 8B vs Llama 3-8B

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 25.3 on the Noometry Index.

Last verified October 10, 2026. 11 shared benchmarks.

Granite 4.2 8B IBM

40.0

Rank #143 Confirmed

Llama 3-8B

Summary

They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 7 categories and Llama 3-8B in 0 categories; 7 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Granite 4.2 8B leads 37.7 to 7.8.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.14 / $0.14 for Llama 3-8B.
Granite 4.2 8B accepts more context: 131K tokens versus 8K.

Side by side

Granite 4.2 8B and Llama 3-8B specifications
	Granite 4.2 8B	Llama 3-8B
Provider	IBM	Meta
Noometry Index	40.0	25.3
Released	—	2024-04-18
Weights	Open	Open
Context window	131K	8K
Max output	118K	8K
Input $ / M tokens	$0.06	$0.14
Output $ / M tokens	$0.25	$0.14
Results tracked	11	34

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

Category by category

Coding Granite 4.2 8B leads

Granite 4.2 8B: 39.9 (#138), Llama 3-8B: 30.5 (#285)

Coding benchmarks
Benchmark	Granite 4.2 8B	Llama 3-8B
LMArena Coding	1379	1152
BigCodeBench Instruct	—	31.9%
BigCodeBench Complete	—	36.9%
HumanEval+	—	56.7%
MBPP+	—	54.8%

Reasoning Granite 4.2 8B leads

Granite 4.2 8B: 25.5 (#130), Llama 3-8B: 13.8 (#321)

Reasoning benchmarks
Benchmark	Granite 4.2 8B	Llama 3-8B
LMArena Hard Prompts	1327	1133
Chess Puzzles	—	0%
DTBench	—	43.9%
Adversarial NLI	—	57.3%
Epoch Capabilities Index	—	116.33
ForecastBench	—	58.6
WinoGrande	—	75.7%

Math Not comparable

Granite 4.2 8B: —, Llama 3-8B: 8.3 (#317)

Math benchmarks
Benchmark	Granite 4.2 8B	Llama 3-8B
OTIS Mock AIME 2024-2025	—	1.9%
LMArena Math	—	1151
MATH Level 5	—	6.1%

Knowledge Granite 4.2 8B leads

Granite 4.2 8B: 37.7 (#144), Llama 3-8B: 7.8 (#303)

Knowledge benchmarks
Benchmark	Granite 4.2 8B	Llama 3-8B
LMArena Expert	1380	1113
GPQA Diamond	—	26.1%
ARC (AI2) Challenge	—	82.8%
MMLU	—	68.8%
OpenBookQA	—	82.6%
TriviaQA	—	67.7%

Multilingual Granite 4.2 8B leads

Granite 4.2 8B: 44.5 (#173), Llama 3-8B: 31.0 (#256)

Multilingual benchmarks
Benchmark	Granite 4.2 8B	Llama 3-8B
LMArena Non-English	1299	1098
LMArena Chinese	1361	1076
LMArena Russian	1283	1109
LMArena French	—	1158
LMArena German	—	1104
LMArena Japanese	—	967
LMArena Korean	—	1003
LMArena Spanish	—	1172

Instruction Following Granite 4.2 8B leads

Granite 4.2 8B: 68.7 (#183), Llama 3-8B: 58.7 (#255)

Instruction Following benchmarks
Benchmark	Granite 4.2 8B	Llama 3-8B
LMArena Instruction Following	1298	1127

Long Context Granite 4.2 8B leads

Granite 4.2 8B: 40.2 (#154), Llama 3-8B: 34.2 (#246)

Long Context benchmarks
Benchmark	Granite 4.2 8B	Llama 3-8B
LMArena Longer Query	1323	1128

Writing & Preference Granite 4.2 8B leads

Granite 4.2 8B: 49.8 (#183), Llama 3-8B: 37.7 (#251)

Writing & Preference benchmarks
Benchmark	Granite 4.2 8B	Llama 3-8B
LMArena Text	1319	1166
LMArena Creative Writing	1238	1150
LMArena Multi-Turn	1299	1152

Frequently asked questions

Is Granite 4.2 8B better than Llama 3-8B?

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 25.3 on the Noometry Index.

Which is cheaper, Granite 4.2 8B or Llama 3-8B?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Llama 3-8B lists at $0.14 and $0.14.

Is Granite 4.2 8B or Llama 3-8B better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 39.9 versus 30.5 in the Noometry coding category.

Which has the bigger context window?

Granite 4.2 8B does, with 131K tokens against 8K.

How many benchmarks do Granite 4.2 8B and Llama 3-8B share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Llama 3-8B has 34.