Granite 4.1 30B

Granite 4.1 30B

IBM · Released Apr 29, 2026 Professional
Intelligence #10 / 576
82.0 Our Score
AA Index #242 / 378
14.7 Artificial Analysis
Input
— Not priced
Output
— Not priced
Context
— Not reported

Analysis Summary

Granite 4.1 30B is IBM's largest model in the Granite 4.1 family, released in April 2026. It shows moderate general reasoning and a reasonable agentic score for its size class, but coding capability is limited and long-context reliability is weak, making it a niche fit rather than a general-purpose workhorse.

For businesses, it is best suited to structured classification, document triage, or lightweight automation where a smaller, potentially self-hosted model is preferred over a frontier API. It is not competitive for complex coding tasks, multi-step agentic workflows, or high-stakes reasoning.

No pricing data is available in this batch, which limits value assessment. Teams evaluating IBM Granite should treat this as a capable small-enterprise model for constrained deployments, not a replacement for frontier reasoning models.

Assessed June 6, 2026

Editorial notes

Granite 4.1 30B is IBM's mid-range open model with moderate reasoning and agentic capability, suited to lighter enterprise tasks but well behind frontier models on coding and complex reasoning.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence2.3Technical1.7Value0Content3.6
Intelligence 2.3/10
Technical 1.7/10
Content 3.6/10
Value 0/10

How Granite 4.1 30B compares

Granite 4.1 30B ranks #242 of 378 AI models we track for overall intelligence, #238 of 315 for coding, #168 of 289 for agentic tasks. Granite 4.1 30B is currently free to use via OpenRouter.

Performance Indices

Source: Artificial Analysis

14.7 Intelligence Index
10.1 Coding Index
22.2 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 48.1% Graduate-level scientific reasoning
HLE 4.2% Humanity's Last Exam
SciCode 25.8% Scientific computing

Technical

TerminalBench Hard 2.3% Agentic terminal tasks
τ²-Bench 42.1% Conversational agent benchmark

Content

IFBench 44.4% Instruction following
LCR 18.7% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Granite 4.1 30B stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

ProviderIBM
Release Date April 29, 2026
Status Active

Frequently asked questions about Granite 4.1 30B

How much does Granite 4.1 30B cost?

Granite 4.1 30B is currently available for free via OpenRouter.

Is Granite 4.1 30B good for coding?

On our coding benchmark index, Granite 4.1 30B ranks #238 of 315 models, placing it in the broader range of the field for code generation and debugging.

Who created Granite 4.1 30B?

Granite 4.1 30B is developed by IBM and was released on April 29, 2026.