# DeepSeek-V2 (MoE-236B, May 2024) vs Gemma 3 4B

> Gemma 3 4B has enough public results to be ranked (#326); 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-3-4b
- Last updated: 2026-10-12
- 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 4B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 35.9.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 40.3 | 28.1 |
| Rank | — | 326 |
| Context | — | 131K |
| Input $/M | — | $0.04 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
- Gemma 3 4B: 35.9 (#215)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1230 |
| BigCodeBench Complete | 59.4% | — |

## Agentic & Tool Use

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 4B: 20.9 (#142)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 4B: 13.2 (#335)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 116.02 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1253 |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Math

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 4B: 16.8 (#292)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.5% |
| LMArena Math | — | 1239 |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 4B: 11.8 (#299)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
| LMArena Expert | — | 1223 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## Multilingual

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 4B: 42.5 (#194)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | — | 1273 |
| LMArena German | — | 1281 |
| LMArena Russian | — | 1294 |

## Instruction Following

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 4B: 65.2 (#225)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | — | 1239 |

## Long Context

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 4B: 38.7 (#194)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | — | 1273 |

## Writing & Preference

- DeepSeek-V2 (MoE-236B, May 2024): —
- Gemma 3 4B: 42.0 (#239)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Gemma 3 4B |
|---|---|---|
| LMArena Text | — | 1291 |
| LMArena Creative Writing | — | 1271 |
| EQ-Bench Creative Writing | — | 1068 |
| LMArena Multi-Turn | — | 1255 |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than Gemma 3 4B?

Gemma 3 4B has enough public results to be ranked (#326); 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 4B better for coding?

DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 35.9 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Gemma 3 4B share?

1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Gemma 3 4B has 22.