# DeepSeek-V2 (MoE-236B, May 2024) vs Gemma 3 27B

> Gemma 3 27B has enough public results to be ranked (#277); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-v2-vs-gemma-3-27b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Gemma 3 27B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 22.1.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 39.7 | 30.5 |
| Rank | — | 277 |
| Context | — | 131K |
| Input $/M | — | $0.08 |
| Output $/M | — | $0.16 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)
- Gemma 3 27B: 22.1 (#329)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
| BigCodeBench Instruct | 48.9% | — |
| LiveBench Coding | — | 39.9% |
| LMArena Coding | — | 1322 |
| BigCodeBench Complete | 59.4% | — |

## Agentic & Tool Use

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 24.9 (#105)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 16.3 (#297)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| Epoch Capabilities Index | 124.78 | 130.04 |
| Kagi LLM Benchmark | — | 40.4% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 43.8% |
| LMArena Hard Prompts | — | 1340 |
| DTBench | — | 52.5% |
| LiveBench Data Analysis | — | 51.5% |
| LMCA | — | 12.3% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| LiveBench | — | 50% |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Math

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 24.4 (#261)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| LiveBench Math | — | 55.4% |
| LMArena Math | — | 1312 |
| MATH Level 5 | — | 74% |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 25.4 (#256)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | — | 47.7% |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1303 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## Multimodal

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 32.0 (#94)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1165 |
| GeoBench | — | 52% |

## Multilingual

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 47.0 (#150)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | — | 1334 |
| LMArena Chinese | — | 1347 |
| LMArena French | — | 1368 |
| LMArena German | — | 1362 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1349 |
| LMArena Spanish | — | 1348 |

## Instruction Following

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 70.8 (#155)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| LiveBench Instruction Following | — | 74.9% |
| LMArena Instruction Following | — | 1321 |

## Long Context

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 27.6 (#288)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| Fiction.LiveBench | — | 33.3% |
| LMArena Longer Query | — | 1333 |

## Writing & Preference

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 27B: 52.7 (#161)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 27B |
|---|---|---|
| LMArena Text | — | 1358 |
| LMArena Creative Writing | — | 1346 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| LMArena Multi-Turn | — | 1344 |
| LiveBench Language | — | 34.6% |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than Gemma 3 27B?

Gemma 3 27B has enough public results to be ranked (#277); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is DeepSeek-V2 (MoE-236B, May 2024) or Gemma 3 27B better for coding?

DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 22.1 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Gemma 3 27B share?

1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Gemma 3 27B has 43.