# Deepseek Coder v2 vs Gemma 3n E4b IT

> Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-gemma-3n-e4b-it
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 2 categories and Gemma 3n E4b IT in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3n E4b IT leads 50.1 to 38.2.

## Snapshot

| | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 35.9 | 37.3 |
| Rank | 220 | 206 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- Gemma 3n E4b IT: 37.0 (#198)

| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1251 | 1268 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- Gemma 3n E4b IT: 19.9 (#247)

| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1284 |
| Kagi LLM Benchmark | — | 31.5% |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- Gemma 3n E4b IT: 35.1 (#188)

| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1241 | 1251 |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- Gemma 3n E4b IT: 34.2 (#198)

| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | 1181 | 1246 |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- Gemma 3n E4b IT: 43.4 (#183)

| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1182 | 1285 |
| LMArena Chinese | 1201 | 1309 |
| LMArena French | 1185 | 1330 |
| LMArena German | 1164 | 1311 |
| LMArena Japanese | 1126 | 1272 |
| LMArena Korean | 1104 | 1259 |
| LMArena Russian | 1188 | 1288 |
| LMArena Spanish | 1153 | 1305 |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- Gemma 3n E4b IT: 66.1 (#210)

| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1180 | 1255 |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- Gemma 3n E4b IT: 38.7 (#191)

| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1219 | 1276 |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- Gemma 3n E4b IT: 50.1 (#186)

| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1191 | 1306 |
| LMArena Creative Writing | 1120 | 1287 |
| LMArena Multi-Turn | 1177 | 1276 |

## FAQ

### Is Deepseek Coder v2 better than Gemma 3n E4b IT?

Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.

### Is Deepseek Coder v2 or Gemma 3n E4b IT better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 37.0 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Gemma 3n E4b IT share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemma 3n E4b IT has 18.