# DeepSeek Coder 6.7B vs Gemma 2B

> Gemma 2B has enough public results to be ranked (#305); 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-2b
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. DeepSeek Coder 6.7B scores higher in 1 category and Gemma 2B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.2 to 28.9.

## Snapshot

| | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 37.1 | 29.1 |
| Rank | — | 305 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.2 (#216)
- Gemma 2B: 28.9 (#300)

| Benchmark | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| HumanEval+ | 71.3% | 20.7% |
| MBPP+ | 65.6% | 34.1% |
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1010 |
| BigCodeBench Complete | 43.8% | — |

## Reasoning

- DeepSeek Coder 6.7B: —
- Gemma 2B: 17.9 (#275)

| Benchmark | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| Epoch Capabilities Index | 88.88 | 93.57 |
| WinoGrande | 57.6% | 65.4% |
| LMArena Hard Prompts | — | 989 |
| BIG-Bench Hard | — | 35.2% |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |

## Math

- DeepSeek Coder 6.7B: —
- Gemma 2B: 27.6 (#237)

| Benchmark | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| GSM8K | 21.3% | 17.7% |
| LMArena Math | — | 1009 |

## Knowledge

- DeepSeek Coder 6.7B: —
- Gemma 2B: —

| Benchmark | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | 42.1% |
| MMLU | 36.4% | 42.3% |
| BoolQ | — | 69.4% |
| TriviaQA | — | 53.2% |

## Multilingual

- DeepSeek Coder 6.7B: —
- Gemma 2B: 23.1 (#289)

| Benchmark | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| LMArena Non-English | — | 958 |
| LMArena Chinese | — | 986 |
| LMArena Russian | — | 937 |

## Instruction Following

- DeepSeek Coder 6.7B: —
- Gemma 2B: 48.8 (#297)

| Benchmark | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | — | 971 |

## Long Context

- DeepSeek Coder 6.7B: —
- Gemma 2B: 29.9 (#286)

| Benchmark | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| LMArena Longer Query | — | 981 |

## Writing & Preference

- DeepSeek Coder 6.7B: —
- Gemma 2B: 24.1 (#303)

| Benchmark | DeepSeek Coder 6.7B | Gemma 2B |
|---|---|---|
| LMArena Text | — | 1002 |
| LMArena Creative Writing | — | 986 |
| LMArena Multi-Turn | — | 945 |

## FAQ

### Is DeepSeek Coder 6.7B better than Gemma 2B?

Gemma 2B has enough public results to be ranked (#305); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 6.7B or Gemma 2B better for coding?

DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.2 versus 28.9 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 6.7B and Gemma 2B share?

7 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Gemma 2B has 23.