# Granite 4.2 30b vs phi-3-medium 14B

> Granite 4.2 30b is the stronger model overall, scoring 41.4 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-30b-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Granite 4.2 30b leads 38.5 to 9.1.

## Snapshot

| | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 41.4 | 29.1 |
| Rank | 126 | 306 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 4.2 30b: 40.4 (#127)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1394 | — |
| BigCodeBench Complete | — | 48.7% |

## Reasoning

- Granite 4.2 30b: 26.7 (#114)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1375 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- Granite 4.2 30b: —
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | — | 17.6% |

## Knowledge

- Granite 4.2 30b: 38.5 (#134)
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1405 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- Granite 4.2 30b: 47.4 (#146)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1340 | — |
| LMArena Chinese | 1415 | — |
| LMArena Russian | 1342 | — |

## Instruction Following

- Granite 4.2 30b: 71.3 (#150)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1346 | — |

## Long Context

- Granite 4.2 30b: 41.4 (#135)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1359 | — |

## Writing & Preference

- Granite 4.2 30b: 54.3 (#147)
- phi-3-medium 14B: —

| Benchmark | Granite 4.2 30b | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1363 | — |
| LMArena Creative Writing | 1294 | — |
| LMArena Multi-Turn | 1340 | — |

## FAQ

### Is Granite 4.2 30b better than phi-3-medium 14B?

Granite 4.2 30b is the stronger model overall, scoring 41.4 to 29.1 on the Noometry Index.

### Is Granite 4.2 30b or phi-3-medium 14B better for coding?

Granite 4.2 30b scores higher on coding benchmarks: 40.4 versus 36.3 in the Noometry coding category.

### How many benchmarks do Granite 4.2 30b and phi-3-medium 14B share?

0 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and phi-3-medium 14B has 13.