Skip to main content

Granite 4.2 30B

IBMOpen WeightApache 2.0 · Commercial OK

Description

IBM Granite 4.2 30B is the flagship dense decoder-only reasoning LLM in the Granite 4.2 family. It supports native think, non-think, and low-effort modes, tool calling, and a 128K native context window with extension to 512K. The 8B and 30B sizes received additional agentic reinforcement learning for multi-step tool use. Open weights on Hugging Face under Apache 2.0. Text-only (not multimodal).

Release Date
2026-08-25
Parameters
30.0B
Context Length
—
Modalities
text

Capability Radar

12
general
31
coding
64
reasoning
44
science
50
agents
0
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability59
48.0
LS
Code Ranking261
43.0
AA
General Ranking492
18.0
AA
Science246
44.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

TAU3-Bench62.0%SR

General

Arena-Hard v267.9%SR

Instruction Following

IFBench77.2%SR

Language

MMLU-Pro77.6%SR

Long Context

RULER 64k90.0%SR
RULER 128k81.4%SR

Math

HMMT2589.2%SR
AIME 202589.2%SR

Reasoning

LiveCodeBench v675.8%SR
GPQANYU + Cohere + Anthropic (2023)66.4%SR
SWE-Bench Verified57.0%SR
ProfBench42.9%SR
SWE-bench Multilingual41.9%SR
Bird-SQL (dev)41.9%SR
SciCode38.8%SR
SWE-Bench ProPrinceton NLP (2024)33.3%SR
Terminal-Bench 2.129.2%SR

Tool Calling

BFCL-V461.4%SR

AA Evaluation Indices

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
64.4
Lcr(Artificial Analysis)
49.0
Scicode(UIUC + Argonne National Lab (2024))
37.8
Coding Index(Artificial Analysis)
29.9
Terminalbench V2 1
26.6
Tau Banking
14.4
Intelligence Index(Artificial Analysis)
12.7
Hle(Center for AI Safety + Scale AI (2025))
11.2
Terminalbench V4 0
0.0

LLM Stats Category Scores

(LLM Stats (zeroeval))
Long Context
90
Instruction Following
80
Language
80
Legal
80
Finance
80
Healthcare
80
Math
70
Creativity
70
Writing
70
Reasoning
60
Frontend Development
60
General
60
Physics
50
Agents
50
Biology
50
Chemistry
50
Tool Calling
50
Knowledge
40
Code
40

Pricing

Input Price$0.16 / 1M tokens
Output Price$0.65 / 1M tokens
Blended Price (3:1)$0.282 / 1M tokens

Speed

Tokens/sec53.7
Time to First Token0.34s
Time to Answer37.55s

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: DeepInfraMost Expensive: IBM
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2IBMPRIMARY
$0.16
$0.65

Compare pricing across different API providers for this model.

External Sources