# Granite 4.0 H Small vs Phi 3 Small 8k Instruct

> Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-phi-3-small-8k-instruct
- 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 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.9 to 52.2.

## Snapshot

| | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 35.9 | 28.8 |
| Rank | 213 | 310 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Phi 3 Small 8k Instruct: 27.4 (#313)

| Benchmark | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1247 | 1102 |
| LiveBench Coding | — | 20.3% |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Phi 3 Small 8k Instruct: 14.2 (#319)

| Benchmark | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1100 |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- Phi 3 Small 8k Instruct: 25.4 (#247)

| Benchmark | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1251 | 1151 |
| Omni-MATH | 29.6% | — |
| LiveBench Math | — | 17.6% |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Phi 3 Small 8k Instruct: 28.5 (#237)

| Benchmark | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1244 | 1067 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Phi 3 Small 8k Instruct: 28.6 (#267)

| Benchmark | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1216 | 1058 |
| LMArena Chinese | 1250 | 1061 |
| LMArena Russian | 1198 | 1111 |
| LMArena Spanish | 1258 | 1111 |
| LMArena French | — | 1134 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Phi 3 Small 8k Instruct: 52.2 (#287)

| Benchmark | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1221 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
| IFEval | 89% | — |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Phi 3 Small 8k Instruct: 33.0 (#262)

| Benchmark | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1240 | 1088 |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Phi 3 Small 8k Instruct: 31.3 (#279)

| Benchmark | Granite 4.0 H Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1241 | 1110 |
| LMArena Creative Writing | 1210 | 1083 |
| LMArena Multi-Turn | 1243 | 1068 |
| WildBench | 73.9% | — |
| LiveBench Language | — | 12.9% |

## FAQ

### Is Granite 4.0 H Small better than Phi 3 Small 8k Instruct?

Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 28.8 on the Noometry Index.

### Is Granite 4.0 H Small or Phi 3 Small 8k Instruct better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 27.4 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and Phi 3 Small 8k Instruct share?

13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Phi 3 Small 8k Instruct has 32.