# DeepSeek Coder 33B vs Gemma 3 12B

> Gemma 3 12B has enough public results to be ranked (#255); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-33b-vs-gemma-3-12b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. DeepSeek Coder 33B scores higher in 1 category and Gemma 3 12B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 37.4 to 31.2.

## Snapshot

| | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 38.3 | 31.8 |
| Rank | — | 255 |
| Context | — | 131K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.15 |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 33B: 37.4 (#180)
- Gemma 3 12B: 31.2 (#276)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| SciCode | — | 17.4% |
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 1281 |
| BigCodeBench Complete | 51.1% | — |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |

## Agentic & Tool Use

- DeepSeek Coder 33B: —
- Gemma 3 12B: 25.3 (#101)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |

## Reasoning

- DeepSeek Coder 33B: —
- Gemma 3 12B: 15.2 (#307)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| Epoch Capabilities Index | 95.74 | 123.49 |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1309 |
| DTBench | — | 48.8% |
| LMCA | — | 4.5% |
| WinoGrande | 62% | — |

## Math

- DeepSeek Coder 33B: —
- Gemma 3 12B: 21.0 (#273)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 16.7% |
| LMArena Math | — | 1307 |
| GSM8K | 35.4% | — |

## Knowledge

- DeepSeek Coder 33B: —
- Gemma 3 12B: 26.5 (#250)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| GPQA Diamond | — | 39.5% |
| Vectara Hallucination Rate | — | 4.4% |
| LMArena Expert | — | 1248 |
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |

## Multimodal

- DeepSeek Coder 33B: —
- Gemma 3 12B: —

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| MindCube | — | 46.7% |

## Multilingual

- DeepSeek Coder 33B: —
- Gemma 3 12B: 45.9 (#160)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | — | 1318 |
| LMArena German | — | 1370 |
| LMArena Russian | — | 1335 |

## Instruction Following

- DeepSeek Coder 33B: —
- Gemma 3 12B: 68.8 (#179)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | — | 1299 |

## Long Context

- DeepSeek Coder 33B: —
- Gemma 3 12B: 40.0 (#157)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | — | 1317 |

## Writing & Preference

- DeepSeek Coder 33B: —
- Gemma 3 12B: 47.7 (#205)

| Benchmark | DeepSeek Coder 33B | Gemma 3 12B |
|---|---|---|
| LMArena Text | — | 1334 |
| LMArena Creative Writing | — | 1331 |
| EQ-Bench Creative Writing | — | 1126 |
| LMArena Multi-Turn | — | 1334 |

## FAQ

### Is DeepSeek Coder 33B better than Gemma 3 12B?

Gemma 3 12B has enough public results to be ranked (#255); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 33B or Gemma 3 12B better for coding?

DeepSeek Coder 33B scores higher on coding benchmarks: 37.4 versus 31.2 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 33B and Gemma 3 12B share?

1 benchmark has published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Gemma 3 12B has 24.