# Amazon Nova Pro vs Granite 4.0 H Small

> Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 31.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-ibm-granite-h-small
- Last updated: 2026-10-11
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 3 categories and Granite 4.0 H Small in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.0 H Small leads 32.0 to 27.4.
- The biggest single-benchmark swing is MMLU-Pro: 67.3% for Amazon Nova Pro and 56.9% for Granite 4.0 H Small.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| Provider | Amazon | IBM |
| Noometry Index | 31.0 | 36.5 |
| Rank | 281 | 214 |
| Context | 300K | — |
| Input $/M | $0.80 | — |
| Output $/M | $3.20 | — |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- Granite 4.0 H Small: 36.4 (#209)

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1270 | 1249 |
| LiveBench Coding | 38.1% | — |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- Granite 4.0 H Small: —

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- Granite 4.0 H Small: 24.4 (#163)

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1240 |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 28.5 (#243)
- Granite 4.0 H Small: 31.4 (#223)

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| Omni-MATH | 24.2% | 29.6% |
| LMArena Math | 1252 | 1247 |
| LiveBench Math | 38% | — |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- Granite 4.0 H Small: 32.0 (#215)

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| MMLU-Pro | 67.3% | 56.9% |
| Vectara Hallucination Rate | 5.1% | 5.2% |
| GPQA (HELM) | 44.6% | 38.3% |
| LMArena Expert | 1211 | 1251 |
| Humanity's Last Exam | 4.4% | — |
| Confabulations | 30.1% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- Granite 4.0 H Small: —

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- Granite 4.0 H Small: 38.6 (#228)

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1234 | 1216 |
| LMArena Chinese | 1244 | 1249 |
| LMArena Russian | 1240 | 1201 |
| LMArena Spanish | 1182 | 1258 |
| LMArena French | 1271 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- Granite 4.0 H Small: 68.7 (#183)

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| IFEval | 81.5% | 89% |
| LMArena Instruction Following | 1235 | 1222 |
| LiveBench Instruction Following | 67.1% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- Granite 4.0 H Small: 37.7 (#213)

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1255 | 1242 |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- Granite 4.0 H Small: 43.8 (#227)

| Benchmark | Amazon Nova Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1259 | 1241 |
| LMArena Creative Writing | 1212 | 1211 |
| WildBench | 77.7% | 73.9% |
| LMArena Multi-Turn | 1246 | 1242 |
| Short-Story Creative Writing | 60.5% | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Granite 4.0 H Small?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 31.0 on the Noometry Index.

### Is Amazon Nova Pro or Granite 4.0 H Small better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 35.1 in the Noometry coding category.

### How many benchmarks do Amazon Nova Pro and Granite 4.0 H Small share?

19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Granite 4.0 H Small has 19.