IBM, open weights

# Granite 4.0 H Small

> Granite 4.0 H Small by IBM. Ranked #214 of 354 with a Noometry Index of 36.5. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/ibm-granite-h-small
- Last updated: 2026-10-10
- Title: Granite 4.0 H Small Benchmarks, Price & Rank (October 2026)

Granite 4.0 H Small by IBM ranks 214th of 354 ranked models on the Noometry Index as of October 2026, with a score of 36.5. Its strongest category is reasoning, where it ranks 163rd.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #214 of 354
- **Index score:** 36.5
- **Evidence:** Confirmed 19 results
- **Provider:** [IBM](https://noometry.com/providers/ibm)
- **Released:** Unknown
- **Weights:** Open weights
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** Not measured
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

Each category score combines every public result we have in that category.

Granite 4.0 H Small category scores

1.  Coding 36.4
2.  Reasoning 24.4
3.  Math 31.4
4.  Knowledge 32.0
5.  Multilingual 38.6
6.  Instruction Following 68.7
7.  Long Context 37.7
8.  Writing & Preference 43.8
9.  020406080

Granite 4.0 H Small category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 36.4 | #209 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 24.4 | #163 | 1 |
| [Math](https://noometry.com/best/math) | 31.4 | #223 | 2 |
| [Knowledge](https://noometry.com/best/knowledge) | 32.0 | #215 | 4 |
| [Multilingual](https://noometry.com/best/multilingual) | 38.6 | #228 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 68.7 | #183 | 2 |
| [Long Context](https://noometry.com/best/long-context) | 37.7 | #213 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 43.8 | #227 | 4 |

## Strengths and weaknesses

Categories where Granite 4.0 H Small places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Granite 4.0 H Small: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 24.4 | +0.8 | #163 of 350, top 47% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 68.7 | −2.5 | #183 of 305, top 60% |
| [Coding](https://noometry.com/best/coding) | 36.4 | −2.3 | #209 of 340, top 62% |

### Weakest categories

Granite 4.0 H Small: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Multilingual](https://noometry.com/best/multilingual) | 38.6 | −8.8 | #228 of 297, top 77% |
| [Writing & Preference](https://noometry.com/best/writing) | 43.8 | −10.0 | #227 of 312, top 73% |
| [Long Context](https://noometry.com/best/long-context) | 37.7 | −3.3 | #213 of 296, top 72% |

## Closest competitors

The models ranked just above and below Granite 4.0 H Small. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Granite 4.0 H Small
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Qwen Plus](https://noometry.com/models/qwen-plus) | #210 | 37.1 | $0.60 | 37 | [Compare](https://noometry.com/compare/ibm-granite-h-small-vs-qwen-plus) |
| [Gemini 2.5 Flash-Lite](https://noometry.com/models/gemini-2-5-flash-lite) | #211 | 37.0 | $0.18 | 172 | [Compare](https://noometry.com/compare/gemini-2-5-flash-lite-vs-ibm-granite-h-small) |
| [o3-mini](https://noometry.com/models/o3-mini) | #212 | 36.7 | $1.93 | — | [Compare](https://noometry.com/compare/ibm-granite-h-small-vs-o3-mini) |
| [Llama 3.1 Nemotron Ultra 253b v1](https://noometry.com/models/llama-3-1-nemotron-ultra-253b-v1) | #213 | 36.7 | — | — | [Compare](https://noometry.com/compare/ibm-granite-h-small-vs-llama-3-1-nemotron-ultra-253b-v1) |
| [Command A](https://noometry.com/models/command-a) | #215 | 36.5 | $4.38 | 28 | [Compare](https://noometry.com/compare/command-a-vs-ibm-granite-h-small) |
| [Grok Build 0.1](https://noometry.com/models/grok-build-0-1) | #216 | 36.4 | $1.25 | — | [Compare](https://noometry.com/compare/grok-build-0-1-vs-ibm-granite-h-small) |
| [gpt-oss-120b](https://noometry.com/models/gpt-oss-120b) | #217 | 36.3 | $0.0703 | 55 | [Compare](https://noometry.com/compare/gpt-oss-120b-vs-ibm-granite-h-small) |
| [Mistral Medium](https://noometry.com/models/mistral-medium) | #218 | 36.3 | $3 | 68 | [Compare](https://noometry.com/compare/ibm-granite-h-small-vs-mistral-medium) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Granite 4.0 H Small Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1249 | #226 of 294, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Reasoning

Granite 4.0 H Small Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1240 | #227 of 297, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Math

Granite 4.0 H Small Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Omni-MATH](https://noometry.com/benchmarks/omni-math) | 29.6% | #38 of 57, top 67% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1247 | #215 of 285, top 76% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

Granite 4.0 H Small Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) | 56.9% | #47 of 58, top 82% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 5.2% | #12 of 96, top 13% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) | 38.3% | #46 of 57, top 81% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1251 | #195 of 273, top 72% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

Granite 4.0 H Small Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1216 | #228 of 297, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1249 | #207 of 285, top 73% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1201 | #233 of 283, top 83% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1258 | #180 of 226, top 80% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Granite 4.0 H Small Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [IFEval](https://noometry.com/benchmarks/ifeval) | 89% | #11 of 57, top 20% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1222 | #229 of 298, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Granite 4.0 H Small Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1242 | #225 of 291, top 78% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Granite 4.0 H Small Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1241 | #227 of 297, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1211 | #227 of 295, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [WildBench](https://noometry.com/benchmarks/wildbench) | 73.9% | #47 of 57, top 83% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1242 | #226 of 295, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## Compare Granite 4.0 H Small

-   [Granite 4.0 H Small vs Llama 3.1 Nemotron Ultra 253b v1](https://noometry.com/compare/ibm-granite-h-small-vs-llama-3-1-nemotron-ultra-253b-v1)
-   [Granite 4.0 H Small vs Command A](https://noometry.com/compare/command-a-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs o3-mini](https://noometry.com/compare/ibm-granite-h-small-vs-o3-mini)
-   [Granite 4.0 H Small vs Grok Build 0.1](https://noometry.com/compare/grok-build-0-1-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs Gemini 2.5 Flash-Lite](https://noometry.com/compare/gemini-2-5-flash-lite-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs gpt-oss-120b](https://noometry.com/compare/gpt-oss-120b-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs Kimi K3](https://noometry.com/compare/ibm-granite-h-small-vs-kimi-k3)
-   [Granite 4.0 H Small vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs Qwen3.8 Max](https://noometry.com/compare/ibm-granite-h-small-vs-qwen3-8-max)
-   [Granite 4.0 H Small vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-ibm-granite-h-small)
-   [Granite 4.0 H Small vs Muse Spark 1.3](https://noometry.com/compare/ibm-granite-h-small-vs-muse-spark-1-3)

## Other IBM models

-   [Granite 4.2 30b](https://noometry.com/models/granite-4-2-30b)41.8
-   [Granite 4.2 8B](https://noometry.com/models/granite-4-2-8b)40.5
-   [Granite 4.2 3b](https://noometry.com/models/granite-4-2-3b)39.4
-   [Granite 4.1 8b](https://noometry.com/models/granite-4-1-8b)37.4
-   [Granite 3.1 2b Instruct](https://noometry.com/models/granite-3-1-2b-instruct)33.2
-   [Granite 3.1 8b Instruct](https://noometry.com/models/granite-3-1-8b-instruct)32.4
-   [Granite 3.0 8b Instruct](https://noometry.com/models/granite-3-0-8b-instruct)31.6
-   [Granite 3.0 2b Instruct](https://noometry.com/models/granite-3-0-2b-instruct)30.8

## Frequently asked questions

### How good is Granite 4.0 H Small?

Granite 4.0 H Small by IBM ranks 214th of 354 ranked models on the Noometry Index as of October 2026, with a score of 36.5. Its strongest category is reasoning, where it ranks 163rd.

### Is Granite 4.0 H Small open source?

Yes. Granite 4.0 H Small's weights are downloadable; check the license for commercial terms.

### What are Granite 4.0 H Small's strengths and weaknesses?

Relative to other ranked models, Granite 4.0 H Small places best in reasoning, instruction following, coding and lowest in multilingual, writing & preference, long context.

### What is Granite 4.0 H Small best at?

Its best category is reasoning, where it ranks 163rd on Noometry.

### Cite this page

Noometry. (2026). Granite 4.0 H Small benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/ibm-granite-h-small

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/ibm-granite-h-small.md).