# Granite 4.2 3b vs Phi 3 Medium 4k Instruct

> Granite 4.2 3b is the stronger model overall, scoring 39.0 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-3b-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 7 categories and Phi 3 Medium 4k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 4.2 3b leads 47.9 to 34.3.

## Snapshot

| | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 39.0 | 32.4 |
| Rank | 163 | 246 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.2 3b: 39.4 (#146)
- Phi 3 Medium 4k Instruct: 32.3 (#263)

| Benchmark | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1363 | 1130 |

## Reasoning

- Granite 4.2 3b: 25.0 (#136)
- Phi 3 Medium 4k Instruct: 20.8 (#214)

| Benchmark | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1308 | 1127 |

## Math

- Granite 4.2 3b: —
- Phi 3 Medium 4k Instruct: 30.9 (#202)

| Benchmark | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | — | 1173 |

## Knowledge

- Granite 4.2 3b: 35.6 (#169)
- Phi 3 Medium 4k Instruct: 29.6 (#226)

| Benchmark | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1313 | 1108 |

## Multilingual

- Granite 4.2 3b: 42.4 (#193)
- Phi 3 Medium 4k Instruct: 30.8 (#258)

| Benchmark | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1268 | 1094 |
| LMArena Chinese | 1268 | 1108 |
| LMArena Russian | 1249 | 1145 |
| LMArena French | — | 1109 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Spanish | — | 1095 |

## Instruction Following

- Granite 4.2 3b: 67.2 (#195)
- Phi 3 Medium 4k Instruct: 57.8 (#263)

| Benchmark | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1271 | 1114 |

## Long Context

- Granite 4.2 3b: 39.3 (#179)
- Phi 3 Medium 4k Instruct: 33.9 (#250)

| Benchmark | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1293 | 1120 |

## Writing & Preference

- Granite 4.2 3b: 47.9 (#202)
- Phi 3 Medium 4k Instruct: 34.3 (#267)

| Benchmark | Granite 4.2 3b | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1295 | 1138 |
| LMArena Creative Writing | 1215 | 1106 |
| LMArena Multi-Turn | 1293 | 1088 |

## FAQ

### Is Granite 4.2 3b better than Phi 3 Medium 4k Instruct?

Granite 4.2 3b is the stronger model overall, scoring 39.0 to 32.4 on the Noometry Index.

### Is Granite 4.2 3b or Phi 3 Medium 4k Instruct better for coding?

Granite 4.2 3b scores higher on coding benchmarks: 39.4 versus 32.3 in the Noometry coding category.

### How many benchmarks do Granite 4.2 3b and Phi 3 Medium 4k Instruct share?

11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.