Granite 4.2 3B

IBM

Release Date

2026-08-25

Parameters

—

Context Length

—

Modalities

—

Capability Radar

general

coding

reasoning

science

agents

multimodal

Rankings

Domain	#Rank	Score	Source
Code Ranking	404	24.0	AA
General Ranking	515	21.0	AA
Science	396	35.0	AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

No benchmark data available

AA Evaluation Indices

(Artificial Analysis)

Gpqa(NYU + Cohere + Anthropic (2023))

55.9

Scicode(UIUC + Argonne National Lab (2024))

24.9

Lcr(Artificial Analysis)

24.3

Coding Index(Artificial Analysis)

17.5

Intelligence Index(Artificial Analysis)

14.3

Terminalbench V2 1

13.9

Hle(Center for AI Safety + Scale AI (2025))

6.6

Tau Banking

5.6

LLM Stats Category Scores

(LLM Stats (zeroeval))

No category score data available

Pricing

Input Price$0.03 / 1M tokens

Output Price$0.12 / 1M tokens

Blended Price (3:1)$0.052 / 1M tokens

Speed

Tokens/sec117.3

Time to First Token0.27s

Time to Answer17.32s

Provider Price Ranking

1 providers

ProviderInputOutput

1IBMPRIMARY

$0.03

$0.12

Compare pricing across different API providers for this model.

External Sources

Artificial Analysis