# Granite 4.2 8B vs Granite 4.0 H Small

> Granite 4.2 8B is the stronger model overall, scoring 40.5 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-8b-vs-ibm-granite-h-small
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 6 categories and Granite 4.0 H Small in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 8B leads 38.4 to 32.0.

## Snapshot

| | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 40.5 | 36.5 |
| Rank | 148 | 214 |
| Context | 131K | — |
| Input $/M | $0.06 | — |
| Output $/M | $0.25 | — |
| Weights | Open | Open |

## Coding

- Granite 4.2 8B: 40.5 (#137)
- Granite 4.0 H Small: 36.4 (#209)

| Benchmark | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1380 | 1249 |

## Reasoning

- Granite 4.2 8B: 26.6 (#131)
- Granite 4.0 H Small: 24.4 (#163)

| Benchmark | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1240 |

## Math

- Granite 4.2 8B: —
- Granite 4.0 H Small: 31.4 (#223)

| Benchmark | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| Omni-MATH | — | 29.6% |
| LMArena Math | — | 1247 |

## Knowledge

- Granite 4.2 8B: 38.4 (#145)
- Granite 4.0 H Small: 32.0 (#215)

| Benchmark | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1384 | 1251 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |

## Multilingual

- Granite 4.2 8B: 44.5 (#178)
- Granite 4.0 H Small: 38.6 (#228)

| Benchmark | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1302 | 1216 |
| LMArena Chinese | 1366 | 1249 |
| LMArena Russian | 1285 | 1201 |
| LMArena Spanish | — | 1258 |

## Instruction Following

- Granite 4.2 8B: 68.7 (#184)
- Granite 4.0 H Small: 68.7 (#183)

| Benchmark | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1301 | 1222 |
| IFEval | — | 89% |

## Long Context

- Granite 4.2 8B: 40.3 (#159)
- Granite 4.0 H Small: 37.7 (#213)

| Benchmark | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1324 | 1242 |

## Writing & Preference

- Granite 4.2 8B: 49.6 (#189)
- Granite 4.0 H Small: 43.8 (#227)

| Benchmark | Granite 4.2 8B | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1320 | 1241 |
| LMArena Creative Writing | 1236 | 1211 |
| LMArena Multi-Turn | 1301 | 1242 |
| WildBench | — | 73.9% |

## FAQ

### Is Granite 4.2 8B better than Granite 4.0 H Small?

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 36.5 on the Noometry Index.

### Is Granite 4.2 8B or Granite 4.0 H Small better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 40.5 versus 36.4 in the Noometry coding category.

### How many benchmarks do Granite 4.2 8B and Granite 4.0 H Small share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Granite 4.0 H Small has 19.