Skip to main content
AITier

Granite 4.2 8B

IBMOpen WeightApache 2.0 · Commercial OK

Description

IBM Granite 4.2 8B is a mid-size 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. Like the 30B, it 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
8.0B
Context Length
131K
Modalities
text

Capability Radar

11
general
24
coding
63
reasoning
41
science
40
agents
0
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability102
38.0
LS
Code Ranking295
35.0
AA
General Ranking528
15.0
AA
Science298
39.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

TAU3-Bench58.1%SR

General

Arena-Hard v265.2%SR

Instruction Following

IFBench79.3%SR

Language

MMLU-Pro74.0%SR

Long Context

RULER 64k81.0%SR
RULER 128k71.4%SR

Math

AIME 202586.7%SR
HMMT2578.3%SR

Reasoning

LiveCodeBench v673.2%SR
GPQANYU + Cohere + Anthropic (2023)64.1%SR
SWE-Bench Verified47.7%SR
ProfBench41.2%SR
Bird-SQL (dev)41.1%SR
SciCode36.1%SR
SWE-bench Multilingual30.8%SR
Terminal-Bench 2.120.6%SR
SWE-Bench ProPrinceton NLP (2024)19.1%SR

Tool Calling

BFCL-V452.4%SR

AA Evaluation Indices

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
63.1
Lcr(Artificial Analysis)
45.0
Scicode(UIUC + Argonne National Lab (2024))
31.5
Coding Index(Artificial Analysis)
22.4
Terminalbench V2 1
18.4
Intelligence Index(Artificial Analysis)
11.1
Hle(Center for AI Safety + Scale AI (2025))
9.7
Tau Banking
7.6
Terminalbench V4 0
0.0

LLM Stats Category Scores

(LLM Stats (zeroeval))
Instruction Following
80
Long Context
80
Language
70
Legal
70
Math
70
Finance
70
Healthcare
70
Creativity
70
Writing
70
General
60
Physics
50
Reasoning
50
Frontend Development
50
Biology
50
Chemistry
50
Knowledge
40
Agents
40
Tool Calling
40
Code
30

Pricing

Input Price$0.06 / 1M tokens
Output Price$0.25 / 1M tokens
Blended Price (3:1)$0.107 / 1M tokens
Cache Read Price$0.015 / 1M tokens

Speed

Tokens/sec48.8
Time to First Token0.36s
Time to Answer41.38s

Provider Price Ranking

Provider Price Ranking

6 providers

Cheapest: DeepInfraMost Expensive: CoreWeave
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2IBMPRIMARY
$0.06
$0.25
3OpenRouter
$0.06
$0.25
4Kilo Gateway
$0.06
$0.25
5NanoGPT
$0.1
$0.15
6CoreWeave
$0.1
$0.15

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis