# Granite 4.2 3b vs phi-3-medium 14B

> Granite 4.2 3b is the stronger model overall, scoring 39.4 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-3b-vs-phi-3-medium-14b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Granite 4.2 3b leads 36.3 to 9.1.

## Snapshot

| | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 39.4 | 29.7 |
| Rank | 169 | 306 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.2 3b: 40.0 (#151)
- phi-3-medium 14B: 36.8 (#201)

| Benchmark | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1361 | — |
| BigCodeBench Complete | — | 48.7% |

## Reasoning

- Granite 4.2 3b: 26.0 (#138)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1306 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- Granite 4.2 3b: —
- phi-3-medium 14B: 27.3 (#250)

| Benchmark | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | — | 17.6% |

## Knowledge

- Granite 4.2 3b: 36.3 (#171)
- phi-3-medium 14B: 9.1 (#306)

| Benchmark | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1315 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- Granite 4.2 3b: 42.1 (#198)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1269 | — |
| LMArena Russian | 1249 | — |

## Instruction Following

- Granite 4.2 3b: 67.1 (#200)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1273 | — |

## Long Context

- Granite 4.2 3b: 39.2 (#185)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1291 | — |

## Writing & Preference

- Granite 4.2 3b: 47.2 (#212)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 3b | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1293 | — |
| LMArena Creative Writing | 1205 | — |
| LMArena Multi-Turn | 1290 | — |

## FAQ

### Is Granite 4.2 3b better than phi-3-medium 14B?

Granite 4.2 3b is the stronger model overall, scoring 39.4 to 29.7 on the Noometry Index.

### Is Granite 4.2 3b or phi-3-medium 14B better for coding?

Granite 4.2 3b scores higher on coding benchmarks: 40.0 versus 36.8 in the Noometry coding category.

### How many benchmarks do Granite 4.2 3b and phi-3-medium 14B share?

0 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and phi-3-medium 14B has 13.