# DeepSeek LLM 67B vs Gemma 3n E4b IT

> Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-gemma-3n-e4b-it
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Gemma 3n E4b IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 3n E4b IT leads 34.2 to 7.0.

## Snapshot

| | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 24.9 | 37.3 |
| Rank | 347 | 206 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Gemma 3n E4b IT: 37.0 (#198)

| Benchmark | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1096 | 1268 |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Gemma 3n E4b IT: 19.9 (#247)

| Benchmark | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1284 |
| Kagi LLM Benchmark | — | 31.5% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Gemma 3n E4b IT: 35.1 (#188)

| Benchmark | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1108 | 1251 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Gemma 3n E4b IT: 34.2 (#198)

| Benchmark | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1246 |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Gemma 3n E4b IT: 43.4 (#183)

| Benchmark | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1073 | 1285 |
| LMArena Chinese | 1132 | 1309 |
| LMArena French | — | 1330 |
| LMArena German | — | 1311 |
| LMArena Japanese | — | 1272 |
| LMArena Korean | — | 1259 |
| LMArena Russian | — | 1288 |
| LMArena Spanish | — | 1305 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Gemma 3n E4b IT: 66.1 (#210)

| Benchmark | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1079 | 1255 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Gemma 3n E4b IT: 38.7 (#191)

| Benchmark | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1092 | 1276 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Gemma 3n E4b IT: 50.1 (#186)

| Benchmark | DeepSeek LLM 67B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1105 | 1306 |
| LMArena Creative Writing | 1067 | 1287 |
| LMArena Multi-Turn | 1082 | 1276 |

## FAQ

### Is DeepSeek LLM 67B better than Gemma 3n E4b IT?

Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or Gemma 3n E4b IT better for coding?

Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Gemma 3n E4b IT share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemma 3n E4b IT has 18.