IBM

Granite 4.2 8B

Aug 25, 2026ReasoningOpen weightsModels.devHugging Face

Compare

Intelligence

11.1

#400 of 744Rank 400 of 744 measured models

Coding

22.4

#215 of 298Rank 215 of 298 measured models

Output speed

120 t/s

#140 of 403Rank 140 of 403 measured models

Price/1M

$0.107

#99 of 659Rank 99 of 659 measured models

Context window

131K

#738 of 1199Rank 738 of 1199 measured models

Cost per task

$0.0236

#25 of 193Rank 25 of 193 measured models

Granite 4.2 8B scores 11.1 on the Artificial Analysis Intelligence Index, ranking 400th of 744 measured models. The closest models on this index are GLM-4.5-Air (11.1), Grok 4 Fast (11.1), and Ling 3.0 Tiny (11.1). At $0.107 per million tokens (3:1 input/output blended price), it is cheaper than GLM-4.5-Air ($0.372) and Grok 4 Fast ($0.275). With an output speed of 120 t/s, it is faster than GLM-4.5-Air (71.1 t/s) and Ling 3.0 Tiny (16.2 t/s).