# DeepSeek Coder 33B vs Gemma 7B

> Gemma 7B has enough public results to be ranked (#299); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-33b-vs-gemma-7b
- Last updated: 2026-10-11
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. DeepSeek Coder 33B scores higher in 1 category and Gemma 7B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 38.0 to 30.5.

## Snapshot

| | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 38.9 | 30.0 |
| Rank | — | 299 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 33B: 38.0 (#184)
- Gemma 7B: 30.5 (#294)

| Benchmark | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| HumanEval+ | 75% | 28.7% |
| MBPP+ | 70.1% | 43.4% |
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 1048 |
| BigCodeBench Complete | 51.1% | — |

## Reasoning

- DeepSeek Coder 33B: —
- Gemma 7B: 19.9 (#249)

| Benchmark | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| Epoch Capabilities Index | 96.32 | 111.99 |
| WinoGrande | 62% | 79% |
| LMArena Hard Prompts | — | 1042 |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |

## Math

- DeepSeek Coder 33B: —
- Gemma 7B: 31.2 (#228)

| Benchmark | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| GSM8K | 35.4% | 46.4% |
| LMArena Math | — | 1066 |

## Knowledge

- DeepSeek Coder 33B: —
- Gemma 7B: 27.3 (#252)

| Benchmark | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | 78.3% |
| MMLU | 39.4% | 66.1% |
| LMArena Expert | — | 1001 |
| BoolQ | — | 83.2% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |

## Multilingual

- DeepSeek Coder 33B: —
- Gemma 7B: 25.1 (#287)

| Benchmark | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| LMArena Non-English | — | 999 |
| LMArena Chinese | — | 1035 |
| LMArena French | — | 1025 |
| LMArena Russian | — | 993 |

## Instruction Following

- DeepSeek Coder 33B: —
- Gemma 7B: 51.5 (#295)

| Benchmark | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | — | 1017 |

## Long Context

- DeepSeek Coder 33B: —
- Gemma 7B: 31.1 (#282)

| Benchmark | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| LMArena Longer Query | — | 1022 |

## Writing & Preference

- DeepSeek Coder 33B: —
- Gemma 7B: 27.1 (#302)

| Benchmark | DeepSeek Coder 33B | Gemma 7B |
|---|---|---|
| LMArena Text | — | 1056 |
| LMArena Creative Writing | — | 1024 |
| LMArena Multi-Turn | — | 963 |

## FAQ

### Is DeepSeek Coder 33B better than Gemma 7B?

Gemma 7B has enough public results to be ranked (#299); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 33B or Gemma 7B better for coding?

DeepSeek Coder 33B scores higher on coding benchmarks: 38.0 versus 30.5 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 33B and Gemma 7B share?

7 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Gemma 7B has 27.