Specifications
Context Window
—
Input Price/1M
—
Output Price/1M
—
Parameters
—
Benchmarks
Granite 4.0 H 350M results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Agentic
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 0.0 | 100.0 | — |
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SciCode | 2.0 | 100.0 | — |
| LiveCodeBench | 2.0 | 100.0 | Artificial Analysis official API |
| AA Coding Index | 0.6 | 100.0 | Artificial Analysis official API |
Knowledge
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 13.0 | 100.0 | — |
Long Context
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 0.0 | 100.0 | — |
Math
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Math Index | 1.3 | 100.0 | Artificial Analysis official API |
| AIME 2025 | 1.0 | 100.0 | Artificial Analysis official API |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 5.4 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| GPQA Diamond | 26.0 | 100.0 | Artificial Analysis official API |
| IFBench | 18.0 | 100.0 | — |
| MMLU Pro | 12.7 | 100.0 | Artificial Analysis official API |
| HLE | 6.0 | 100.0 | — |
Tool Use
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 15.0 | 100.0 | — |
Information
- Release date
- October 28, 2025
- Tool Calling
- ❌ Not supported
- Vision
- ❌ Not supported
- Audio
- ❌ Not supported
Full Analysis: Granite 4.0 H 350M
What is Granite 4.0 H 350M?
Granite 4.0 H 350M is an AI model developed by IBM, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via IBM's cloud API.
Pricing & Costs in 2026
Granite 4.0 H 350M does not have public per-token pricing available at this time. Some models offer access via enterprise plans or research programs. Check IBM's official website for up-to-date availability and pricing.
Benchmarks & Performance
Granite 4.0 H 350M was evaluated on 14 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, Math, overall, Reasoning, Tool Use. Results show moderate performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
Granite 4.0 H 350M specializes in text, offering advanced capabilities for creating and processing text content.
Comparison with Alternatives
In the 2026 AI model ecosystem, Granite 4.0 H 350M competes directly with similarly capable models. IBM competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is Granite 4.0 H 350M?
Granite 4.0 H 350M is an AI model developed by IBM. It is a text model.
How much does Granite 4.0 H 350M cost?
Granite 4.0 H 350M does not have public per-token pricing available at this time. Check IBM's official website for up-to-date information.
How does Granite 4.0 H 350M compare with other models?
In available benchmarks, Granite 4.0 H 350M scored: Terminal-Bench Hard: 0/100, SciCode: 2/100, LiveCodeBench: 2/100. See the full table above for a detailed comparison.
Is Granite 4.0 H 350M open source?
No, Granite 4.0 H 350M is a proprietary model from IBM. It is available via cloud API. For open source alternatives, check our open source model ranking.
What is Granite 4.0 H 350M best for?
Granite 4.0 H 350M excels at general-purpose language tasks.
Last updated: June 01, 2026 • View methodology →