# DeepSeek Coder 6.7B vs Gemma 3 4B

> Gemma 3 4B has enough public results to be ranked (#320); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-6-7b-vs-gemma-3-4b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. DeepSeek Coder 6.7B scores higher in 0 categories and Gemma 3 4B in 1 category, but none of those gaps is larger than the uncertainty.

## Snapshot

| | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 37.1 | 27.9 |
| Rank | — | 320 |
| Context | — | 131K |
| Input $/M | — | $0.04 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.2 (#216)
- Gemma 3 4B: 35.3 (#214)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1230 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |

## Agentic & Tool Use

- DeepSeek Coder 6.7B: —
- Gemma 3 4B: 20.7 (#134)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |

## Reasoning

- DeepSeek Coder 6.7B: —
- Gemma 3 4B: 12.7 (#330)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| Epoch Capabilities Index | 88.88 | 116.02 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1253 |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| WinoGrande | 57.6% | — |

## Math

- DeepSeek Coder 6.7B: —
- Gemma 3 4B: 15.8 (#286)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.5% |
| LMArena Math | — | 1239 |
| GSM8K | 21.3% | — |

## Knowledge

- DeepSeek Coder 6.7B: —
- Gemma 3 4B: 11.8 (#294)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
| LMArena Expert | — | 1223 |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |

## Multilingual

- DeepSeek Coder 6.7B: —
- Gemma 3 4B: 42.7 (#189)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | — | 1273 |
| LMArena German | — | 1281 |
| LMArena Russian | — | 1294 |

## Instruction Following

- DeepSeek Coder 6.7B: —
- Gemma 3 4B: 65.4 (#219)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | — | 1239 |

## Long Context

- DeepSeek Coder 6.7B: —
- Gemma 3 4B: 38.6 (#189)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | — | 1274 |

## Writing & Preference

- DeepSeek Coder 6.7B: —
- Gemma 3 4B: 42.2 (#234)

| Benchmark | DeepSeek Coder 6.7B | Gemma 3 4B |
|---|---|---|
| LMArena Text | — | 1291 |
| LMArena Creative Writing | — | 1270 |
| EQ-Bench Creative Writing | — | 1068 |
| LMArena Multi-Turn | — | 1255 |

## FAQ

### Is DeepSeek Coder 6.7B better than Gemma 3 4B?

Gemma 3 4B has enough public results to be ranked (#320); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 6.7B or Gemma 3 4B better for coding?

They score almost the same on coding (35.2 vs 35.3); test both on your own repository before choosing.

### How many benchmarks do DeepSeek Coder 6.7B and Gemma 3 4B share?

1 benchmark has published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Gemma 3 4B has 22.