Provider logo

Granite 4.1 8B

ibm-granite/granite-4.1-8b
Provider logo

Granite 4.1 8B

ibm-granite/granite-4.1-8b

IBM's Granite 4.1 8B is a dense, decoder-only 8-billion-parameter instruction model built for enterprise text workflows, including tool calling, retrieval-augmented generation, code generation with fill-in-the-middle support, summarization, classification, extraction, and multilingual assistance.

Added Apr 29, 2026

Model weights

Context Window

131.1K

Max Output

131.1K

Input Price (Auto)

$0.050/1M

Output Price (Auto)

$0.100/1M

Cache Read (Auto)

$0.050/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

6.4

Better than 18% of models compared

Coding Index

9.5

Better than 9% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

43.3%

Better than 19% of models compared

HLE

Humanity's Last Exam

3.8%

Better than 11% of models compared

IFBench

Instruction-following benchmark

38.6%

Better than 35% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

27.8%

Better than 33% of models compared

AA-LCR

Long context reasoning evaluation

11.3%

Better than 21% of models compared

CritPt

Research-level physics reasoning

0.0%

Coding

SciCode

Python programming for scientific computing

21.8%

Better than 22% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

0.0%

Better than 5% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

12.3%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

87.1%

Last updated Aug 18, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…