# Granite 4.0 H Small vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 43.8 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Step 5 Preview leads 50.6 to 35.8.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 35.9 | 43.8 |
| Rank | 213 | 78 |
| Context | — | 1.02M |
| Input $/M | — | $1 |
| Output $/M | — | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Step 5 Preview: 50.6 (#40)

| Benchmark | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1569 |
| SciCode | — | 58.9% |
| LMArena Coding | 1247 | — |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Step 5 Preview: 38.0 (#58)

| Benchmark | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| LMArena Hard Prompts | 1240 | — |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- Step 5 Preview: —

| Benchmark | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| Omni-MATH | 29.6% | — |
| LMArena Math | 1251 | — |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Step 5 Preview: —

| Benchmark | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1244 | — |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Step 5 Preview: —

| Benchmark | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1250 | — |
| LMArena Russian | 1198 | — |
| LMArena Spanish | 1258 | — |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Step 5 Preview: —

| Benchmark | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| IFEval | 89% | — |
| LMArena Instruction Following | 1221 | — |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Step 5 Preview: —

| Benchmark | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1240 | — |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Step 5 Preview: —

| Benchmark | Granite 4.0 H Small | Step 5 Preview |
|---|---|---|
| LMArena Text | 1241 | — |
| LMArena Creative Writing | 1210 | — |
| WildBench | 73.9% | — |
| LMArena Multi-Turn | 1243 | — |

## FAQ

### Is Granite 4.0 H Small better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 43.8 to 35.9 on the Noometry Index.

### Is Granite 4.0 H Small or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 50.6 versus 35.8 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and Step 5 Preview share?

0 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Step 5 Preview has 3.