# Granite 3.1 2b Instruct vs Granite 4.0 H Small

> Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 33.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-2b-instruct-vs-ibm-granite-h-small
- Last updated: 2026-10-12
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 1 category and Granite 4.0 H Small in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.7 to 57.7.

## Snapshot

| | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 33.2 | 36.5 |
| Rank | 247 | 214 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 3.1 2b Instruct: 33.4 (#257)
- Granite 4.0 H Small: 36.4 (#209)

| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1149 | 1249 |

## Reasoning

- Granite 3.1 2b Instruct: 22.0 (#209)
- Granite 4.0 H Small: 24.4 (#163)

| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1240 |

## Math

- Granite 3.1 2b Instruct: 33.1 (#206)
- Granite 4.0 H Small: 31.4 (#223)

| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1159 | 1247 |
| Omni-MATH | — | 29.6% |

## Knowledge

- Granite 3.1 2b Instruct: 30.8 (#224)
- Granite 4.0 H Small: 32.0 (#215)

| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1131 | 1251 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |

## Multilingual

- Granite 3.1 2b Instruct: 29.1 (#269)
- Granite 4.0 H Small: 38.6 (#228)

| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1068 | 1216 |
| LMArena Chinese | 1139 | 1249 |
| LMArena Russian | 1063 | 1201 |
| LMArena Spanish | — | 1258 |

## Instruction Following

- Granite 3.1 2b Instruct: 57.7 (#264)
- Granite 4.0 H Small: 68.7 (#183)

| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1116 | 1222 |
| IFEval | — | 89% |

## Long Context

- Granite 3.1 2b Instruct: 35.0 (#244)
- Granite 4.0 H Small: 37.7 (#213)

| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1155 | 1242 |

## Writing & Preference

- Granite 3.1 2b Instruct: 34.1 (#274)
- Granite 4.0 H Small: 43.8 (#227)

| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1127 | 1241 |
| LMArena Creative Writing | 1116 | 1211 |
| LMArena Multi-Turn | 1099 | 1242 |
| WildBench | — | 73.9% |

## FAQ

### Is Granite 3.1 2b Instruct better than Granite 4.0 H Small?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 33.2 on the Noometry Index.

### Is Granite 3.1 2b Instruct or Granite 4.0 H Small better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 33.4 in the Noometry coding category.

### How many benchmarks do Granite 3.1 2b Instruct and Granite 4.0 H Small share?

12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Granite 4.0 H Small has 19.