# Granite 4.0 H Small vs Step 3

> Step 3 is the stronger model overall, scoring 39.9 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.5 to 44.0.

## Snapshot

| | Granite 4.0 H Small | Step 3 |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 35.9 | 39.9 |
| Rank | 213 | 145 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Step 3: 39.5 (#144)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Coding | 1247 | 1367 |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Step 3: 27.6 (#102)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- Step 3: 34.9 (#148)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Math | 1251 | 1366 |
| Omni-MATH | 29.6% | — |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Step 3: 36.2 (#161)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Expert | 1244 | 1333 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |

## Multimodal

- Granite 4.0 H Small: —
- Step 3: 34.9 (#81)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Step 3: 46.5 (#154)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Non-English | 1216 | 1327 |
| LMArena Chinese | 1250 | 1396 |
| LMArena Russian | 1198 | 1331 |
| LMArena Spanish | 1258 | 1372 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Step 3: 70.6 (#159)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1221 | 1332 |
| IFEval | 89% | — |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Step 3: 40.3 (#152)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Longer Query | 1240 | 1326 |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Step 3: 54.5 (#146)

| Benchmark | Granite 4.0 H Small | Step 3 |
|---|---|---|
| LMArena Text | 1241 | 1351 |
| LMArena Creative Writing | 1210 | 1322 |
| LMArena Multi-Turn | 1243 | 1340 |
| WildBench | 73.9% | — |

## FAQ

### Is Granite 4.0 H Small better than Step 3?

Step 3 is the stronger model overall, scoring 39.9 to 35.9 on the Noometry Index.

### Is Granite 4.0 H Small or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 39.5 versus 35.8 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and Step 3 share?

13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Step 3 has 17.