Granite 4.1 30B

Name: Granite 4.1 30B
Author: IBM

IBM🇺🇸 United States

active

Compare with other models →

Context window131K tokens

Version History

4.1minorApril 29, 2026

Granite 4.1 30B introduces enhanced tool-calling, improved instruction following through updated SFT-RL pipeline, and 131K context window. Released under Apache 2.0 license with competitive performance on code and reasoning benchmarks.

Benchmark Scores

Full leaderboard →

10.4 index

AA Coding Index

Artificial Analysis, Oct 2026 ↗

7.4 index

AA Intelligence Index

Artificial Analysis, Oct 2026 ↗

45.8%

GPQA

Hugging Face model card, May 2026 ↗

88.4%

HumanEval

Hugging Face model card, May 2026 ↗

80.2%

MMLU

Hugging Face model card, May 2026 ↗

64.1%

MMLU-Pro

Hugging Face model card, May 2026 ↗

Coverage

model releaseIBM

IBM Releases Granite 4.1 30B With 131K Context Window and Enhanced Tool-Calling

IBM released Granite 4.1 30B, a 30-billion parameter instruction-following model with a 131,072 token context window. The model scores 80.16 on MMLU 5-shot and 88.41 on HumanEval pass@1, with enhanced tool-calling capabilities following OpenAI's function definition schema.

May 1, 2026 · 5:06 PM2 min read

IBM Granite open-source