Granite 4.0 H 1B
Intelligence
8
#491/523
Coding
2.7
#403/429
Math
6.3
#243/265
Speed
—
Pricing
—
Granite 4.0 H 1B is IBM’s latest model designed for various applications in data processing and analysis. It features an Intelligence Index of 8, indicating strong analytical capabilities, while its Coding Index of 2.7 suggests limited coding functionality. The model is priced at $0 per million tokens, making it accessible for professional users.
When to Use Granite 4.0 H 1B
✓ Best For
- Data analysis and interpretation.
- Business intelligence applications.
- Automated reporting and insights generation.
✗ Not Ideal For
- High-speed processing needs due to a speed of 0 tok/sec.
- Complex coding tasks due to a low Coding Index.
How Granite 4.0 H 1B Compares
Intelligence Index · Higher is better
Liquid AIIBMAI21 LabsAlibaba
Benchmark Profile
Coding Index
GoogleAllen Institute for AIIBMAI21 LabsLG AI Research
Math Index
MicrosoftIBMOpenAI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (12)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 8 | |
| Coding Index | 2.7 | |
| Math Index | 6.3 | |
| MMLU-Pro | 277% | |
| GPQA | 263% | |
| LiveCodeBench | 115% | |
| HLE | 5% | |
| SciCode | 8.2% | |
| IFBench | 26.2% | |
| LCR | 6.3% | |
| Tau2 | 19.6% | |
| AIME 2025 | 6.3% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Granite 4.0 H 1B released?
Granite 4.0 H 1B was released on October 28, 2025.
Who created Granite 4.0 H 1B?
Granite 4.0 H 1B was created by IBM.
How intelligent is Granite 4.0 H 1B?
Granite 4.0 H 1B scores 8 on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 8).
How verbose is Granite 4.0 H 1B?
When evaluated on the Intelligence Index, Granite 4.0 H 1B generated 2.9M output tokens, which is very competitive compared to other open weight non-reasoning models of similar size (median: 6.6M).
Is Granite 4.0 H 1B a reasoning model?
No, Granite 4.0 H 1B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Granite 4.0 H 1B support?
Granite 4.0 H 1B supports text input.
What output modalities does Granite 4.0 H 1B support?
Granite 4.0 H 1B supports text output.
Can Granite 4.0 H 1B process images?
No, Granite 4.0 H 1B does not support image input. It can only process text.
Is Granite 4.0 H 1B multimodal?
No, Granite 4.0 H 1B is not multimodal. It only supports text input.
What is the context window of Granite 4.0 H 1B?
Granite 4.0 H 1B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Granite 4.0 H 1B open source?
Yes, Granite 4.0 H 1B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Granite 4.0 H 1B have?
Granite 4.0 H 1B has 1.5 billion parameters.
What is the license for Granite 4.0 H 1B?
Granite 4.0 H 1B is released under the Apache 2.0 license. This license allows commercial use.
How does Granite 4.0 H 1B perform on benchmarks?
Granite 4.0 H 1B achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is Granite 4.0 H 1B available via API?
Granite 4.0 H 1B is an open weights model that can be self-hosted.
