IBMLanguage model
Granite-4.0-H-Small
Granite-4.0-H-Small has no overall index value yet because there are too few independent benchmark results.
PopularityRank 388 of 785
36out of 100same as last month
based on search, usage and attention
Summary
Granite-4.0-H-Small combines a hybrid 32-billion-parameter architecture with about 9 billion active and up to 128K context. IBM documents fill-in-the-middle and lists twelve supported languages, including German. The open weights use Apache 2.0.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 31 published benchmark results
Page 1 of 3
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
CritPt v2: Overall (Show measurement, test conditions, and source)
- Source value
- 0
- Score
- 0
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- v2
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- disputed
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Granite 4.0 H Small (release granite-4-0-h-small, row granite-4-0-h-small, UUID 5dba8d07-9992-483c-81db-dac97cb15ba8, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/5dba8d07-9992-483c-81db-dac97cb15ba8/granite-4-0-h-small/granite-4-0-h-small. Source model name: Granite-4.0-H-Small. Provider reported by source: IBM. Model snapshot: Granite 4.0 H Small. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: non-reasoning. Reasoning effort: none. Score display: 0.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Granite 4.0 H Small (release granite-4-0-h-small, row granite-4-0-h-small, UUID 5dba8d07-9992-483c-81db-dac97cb15ba8, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: non-reasoning. Reasoning effort: none
- Context
- This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 31.496598639455797
- Score
- 31.496598639455797
- Metric
- IFBench prompt-level loose accuracy (pass@1)
- Unit
- %
- Benchmark version
- AA test set: 294 questions
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- superseded
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Granite 4.0 H Small (release granite-4-0-h-small, row granite-4-0-h-small, UUID 5dba8d07-9992-483c-81db-dac97cb15ba8, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/5dba8d07-9992-483c-81db-dac97cb15ba8/granite-4-0-h-small/granite-4-0-h-small. Source model name: Granite-4.0-H-Small. Provider reported by source: IBM. Model snapshot: Granite 4.0 H Small. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none. Score display: 31.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Granite 4.0 H Small (release granite-4-0-h-small, row granite-4-0-h-small, UUID 5dba8d07-9992-483c-81db-dac97cb15ba8, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.. This result is retained as historical evidence and is not interchangeable with current results.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 31.496598639455797
- Score
- 31.496598639455797
- Metric
- IFBench prompt-level loose accuracy (pass@1)
- Unit
- %
- Benchmark version
- AA test set: 294 questions
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-11-07
- Methodology
- Exact AA configuration: Granite 4.0 H Small (release granite-4-0-h-small, row granite-4-0-h-small, UUID 5dba8d07-9992-483c-81db-dac97cb15ba8, reasoning=false, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/5dba8d07-9992-483c-81db-dac97cb15ba8/granite-4-0-h-small/granite-4-0-h-small. Source model name: Granite-4.0-H-Small. Provider reported by source: IBM. Model snapshot: Granite 4.0 H Small. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none. Score display: 31.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Granite 4.0 H Small (release granite-4-0-h-small, row granite-4-0-h-small, UUID 5dba8d07-9992-483c-81db-dac97cb15ba8, reasoning=false, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.
AGI EVAL (Show measurement, test conditions, and source)
- Source value
- 70.63
- Score
- 70.63
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied. Table setup: 0-shot, CoT.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
AlpacaEval 2.0 (Show measurement, test conditions, and source)
- Source value
- 42.48
- Score
- 42.48
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
IFEval Instruct Strict (Show measurement, test conditions, and source)
- Source value
- 89.87
- Score
- 89.87
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied. Table setup: Instruct, Strict.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
IFEval Prompt Strict (Show measurement, test conditions, and source)
- Source value
- 85.22
- Score
- 85.22
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied. Table setup: Prompt, Strict.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
ArenaHard (Show measurement, test conditions, and source)
- Source value
- 46.48
- Score
- 46.48
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
GSM8K Symbolic (Show measurement, test conditions, and source)
- Source value
- 87.38
- Score
- 87.38
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied. Table setup: 8-shot.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
Minerva Math (Show measurement, test conditions, and source)
- Source value
- 74
- Score
- 74
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied. Table setup: 0-shot, CoT.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
DeepMind Math (Show measurement, test conditions, and source)
- Source value
- 59.33
- Score
- 59.33
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied. Table setup: 0-shot, CoT.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
HumanEval+ (Show measurement, test conditions, and source)
- Source value
- 83
- Score
- 83
- Metric
- pass@1
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- IBM Granite 4.0 H-Small model card
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact H Small MoE column in the pinned Granite 4.0 H-Small model card. The card's metric and few-shot setup are retained where supplied. Table setup: pass@1.
- Context
- IBM model-card value. No N or confidence interval is published for this row. Blank table metric fields remain unknown. The source does not state a benchmark-suite version.
Page 1 of 3
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 101 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 7, 2026
Granite-4.0-H-SmallGLM-4.7-Flash 36Nex-N2-Pro 36Aion 3.5 36Claude Opus 4.6 36
Method changes in the timeline, a jump at these points is no market event:
- 1November 1, 2026: Value only with search or usage data, 30-day attention
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Granite-4.0-H-Small, chosen by model line, developer, size, price and release date.
All specifications
Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
Frequently asked questions about Granite-4.0-H-Small
How large is the context window of Granite-4.0-H-Small?
131,072 tokens. That is how much text Granite-4.0-H-Small reads at once, about 200 A4 pages.
Page count as a rule of thumb from Artificial Analysis
GLM-5.1200K
DeepSeek-V3 0324164K
Granite-4.0-H-SmallRank 94 of 103131K
GLM-4.5131K
GPT OSS 120B131K
DeepSeek-V3.2128K
DeepSeek-R1128K
Can I run Granite-4.0-H-Small locally?
Yes, the weights are open.
Stated by IBM
- Open weights
- yes
- License
- Apache 2.0
- Parameters
- 32B
- active per token
- 9B
Sources and data date
Show all 12 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 1 | 0 | 1 |
Without vendor claims and historical or disputed results; those stay labelled in the single values.