# Gemma 3n E4b IT vs phi-3-medium 14B

> Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3n-e4b-it-vs-phi-3-medium-14b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Gemma 3n E4b IT leads 34.2 to 9.1.

## Snapshot

| | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| Provider | Google | Microsoft |
| Noometry Index | 37.3 | 29.7 |
| Rank | 206 | 306 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Gemma 3n E4b IT: 37.0 (#198)
- phi-3-medium 14B: 36.8 (#201)

| Benchmark | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | — | 48.7% |

## Reasoning

- Gemma 3n E4b IT: 19.9 (#247)
- phi-3-medium 14B: —

| Benchmark | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | — |
| LMArena Hard Prompts | 1284 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- Gemma 3n E4b IT: 35.1 (#188)
- phi-3-medium 14B: 27.3 (#250)

| Benchmark | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1251 | — |
| MATH Level 5 | — | 17.6% |

## Knowledge

- Gemma 3n E4b IT: 34.2 (#198)
- phi-3-medium 14B: 9.1 (#306)

| Benchmark | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1246 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- Gemma 3n E4b IT: 43.4 (#183)
- phi-3-medium 14B: —

| Benchmark | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1285 | — |
| LMArena Chinese | 1309 | — |
| LMArena French | 1330 | — |
| LMArena German | 1311 | — |
| LMArena Japanese | 1272 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1288 | — |
| LMArena Spanish | 1305 | — |

## Instruction Following

- Gemma 3n E4b IT: 66.1 (#210)
- phi-3-medium 14B: —

| Benchmark | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1255 | — |

## Long Context

- Gemma 3n E4b IT: 38.7 (#191)
- phi-3-medium 14B: —

| Benchmark | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1276 | — |

## Writing & Preference

- Gemma 3n E4b IT: 50.1 (#186)
- phi-3-medium 14B: —

| Benchmark | Gemma 3n E4b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1306 | — |
| LMArena Creative Writing | 1287 | — |
| LMArena Multi-Turn | 1276 | — |

## FAQ

### Is Gemma 3n E4b IT better than phi-3-medium 14B?

Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 29.7 on the Noometry Index.

### Is Gemma 3n E4b IT or phi-3-medium 14B better for coding?

They score almost the same on coding (37.0 vs 36.8); test both on your own repository before choosing.

### How many benchmarks do Gemma 3n E4b IT and phi-3-medium 14B share?

0 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and phi-3-medium 14B has 13.