Model comparison

Granite 4.2 8B vs Sonar

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 37.8 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

Granite 4.2 8B IBM

40.0

Rank #143 Confirmed

Sonar

Perplexity

37.8

Rank #184 Confirmed

Summary

The widest gap is in reasoning, where Granite 4.2 8B leads 25.5 to 20.3.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $1 / $1 for Sonar.
Granite 4.2 8B accepts more context: 131K tokens versus 128K.
Granite 4.2 8B has downloadable open weights; the other is API-only.

Side by side

Granite 4.2 8B and Sonar specifications
	Granite 4.2 8B	Sonar
Provider	IBM	Perplexity
Noometry Index	40.0	37.8
Released	—	2024-01-01
Weights	Open	Proprietary
Context window	131K	128K
Max output	118K	4K
Input $ / M tokens	$0.06	$1
Output $ / M tokens	$0.25	$1
Results tracked	11	7

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), Sonar: 35.1 (#217)

Coding benchmarks
Benchmark	Granite 4.2 8B	Sonar
LiveBench Coding	—	35.1%
LMArena Coding	1379	—

Reasoning Granite 4.2 8B leads

Granite 4.2 8B: 25.5 (#130), Sonar: 20.3 (#221)

Reasoning benchmarks
Benchmark	Granite 4.2 8B	Sonar
LiveBench Reasoning	—	46.3%
LMArena Hard Prompts	1327	—
LiveBench Data Analysis	—	37.9%
LiveBench	—	46.9%

Math Not comparable

Granite 4.2 8B: —, Sonar: 31.3 (#197)

Math benchmarks
Benchmark	Granite 4.2 8B	Sonar
LiveBench Math	—	41.6%

Knowledge Not comparable

Granite 4.2 8B: 37.7 (#144), Sonar: —

Knowledge benchmarks
Benchmark	Granite 4.2 8B	Sonar
LMArena Expert	1380	—

Multilingual Not comparable

Granite 4.2 8B: 44.5 (#173), Sonar: —

Multilingual benchmarks
Benchmark	Granite 4.2 8B	Sonar
LMArena Non-English	1299	—
LMArena Chinese	1361	—
LMArena Russian	1283	—

Instruction Following Sonar leads

Granite 4.2 8B: 68.7 (#183), Sonar: 71.5 (#146)

Instruction Following benchmarks
Benchmark	Granite 4.2 8B	Sonar
LiveBench Instruction Following	—	76.2%
LMArena Instruction Following	1298	—

Long Context Not comparable

Granite 4.2 8B: 40.2 (#154), Sonar: —

Long Context benchmarks
Benchmark	Granite 4.2 8B	Sonar
LMArena Longer Query	1323	—

Writing & Preference Sonar leads

Granite 4.2 8B: 49.8 (#183), Sonar: 52.6 (#166)

Writing & Preference benchmarks
Benchmark	Granite 4.2 8B	Sonar
LMArena Text	1319	—
LMArena Creative Writing	1238	—
LMArena Multi-Turn	1299	—
LiveBench Language	—	44.1%

Frequently asked questions

Is Granite 4.2 8B better than Sonar?

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 37.8 on the Noometry Index.

Which is cheaper, Granite 4.2 8B or Sonar?

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

Is Granite 4.2 8B or Sonar better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 39.9 versus 35.1 in the Noometry coding category.

Which has the bigger context window?

Granite 4.2 8B does, with 131K tokens against 128K.

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

0 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Sonar has 7.