# Granite 4.0 H Small vs Phi-3.5-MoE

> Granite 4.0 H Small has enough public results to be ranked (#213); Phi-3.5-MoE does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-phi-3-5-moe
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Snapshot

| | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 35.9 | — |
| Rank | 213 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- Phi-3.5-MoE: —

| Benchmark | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| LMArena Coding | 1247 | — |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- Phi-3.5-MoE: —

| Benchmark | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| LMArena Hard Prompts | 1240 | — |
| PIQA | — | 88.6% |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- Phi-3.5-MoE: —

| Benchmark | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| Omni-MATH | 29.6% | — |
| LMArena Math | 1251 | — |
| GSM8K | — | 88.7% |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- Phi-3.5-MoE: —

| Benchmark | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1244 | — |
| BoolQ | — | 84.6% |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- Phi-3.5-MoE: —

| Benchmark | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1250 | — |
| LMArena Russian | 1198 | — |
| LMArena Spanish | 1258 | — |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- Phi-3.5-MoE: —

| Benchmark | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| IFEval | 89% | — |
| LMArena Instruction Following | 1221 | — |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- Phi-3.5-MoE: —

| Benchmark | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| LMArena Longer Query | 1240 | — |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- Phi-3.5-MoE: —

| Benchmark | Granite 4.0 H Small | Phi-3.5-MoE |
|---|---|---|
| LMArena Text | 1241 | — |
| LMArena Creative Writing | 1210 | — |
| WildBench | 73.9% | — |
| LMArena Multi-Turn | 1243 | — |

## FAQ

### Is Granite 4.0 H Small better than Phi-3.5-MoE?

Granite 4.0 H Small has enough public results to be ranked (#213); Phi-3.5-MoE does not yet, so treat this comparison as directional.

### How many benchmarks do Granite 4.0 H Small and Phi-3.5-MoE share?

0 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Phi-3.5-MoE has 3.