# DeepSeek LLM 67B vs Gemma 2 27B

> Gemma 2 27B is the stronger model overall, scoring 29.2 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-gemma-2-27b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Gemma 2 27B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 2 27B leads 44.4 to 31.8.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 27.9% for Gemma 2 27B.

## Snapshot

| | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| Provider | DeepSeek | Google |
| Noometry Index | 24.8 | 29.2 |
| Rank | 341 | 302 |
| Context | — | 8K |
| Input $/M | — | $0.65 |
| Output $/M | — | $0.65 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- Gemma 2 27B: 33.5 (#243)

| Benchmark | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| LMArena Coding | 1096 | 1211 |
| BigCodeBench Instruct | — | 42.8% |
| LiveBench Coding | — | 36% |
| BigCodeBench Complete | — | 52.5% |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- Gemma 2 27B: 14.8 (#313)

| Benchmark | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1199 |
| Epoch Capabilities Index | 110.54 | 122.06 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 28.1% |
| DTBench | — | 48% |
| LiveBench Data Analysis | — | 47.9% |
| LMCA | — | 7.1% |
| LiveBench | — | 38.2% |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- Gemma 2 27B: 10.0 (#306)

| Benchmark | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 1.4% |
| LMArena Math | 1108 | 1212 |
| MATH Level 5 | 6.4% | 27.9% |
| LiveBench Math | — | 26.5% |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- Gemma 2 27B: 18.9 (#275)

| Benchmark | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| GPQA Diamond | 24.6% | 36.5% |
| Confabulations | — | 27.1% |
| LMArena Expert | — | 1172 |
| MMLU | — | 75.7% |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- Gemma 2 27B: 38.8 (#221)

| Benchmark | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1073 | 1217 |
| LMArena Chinese | 1132 | 1221 |
| LMArena French | — | 1246 |
| LMArena German | — | 1209 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1174 |
| LMArena Russian | — | 1234 |
| LMArena Spanish | — | 1228 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- Gemma 2 27B: 60.7 (#244)

| Benchmark | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1206 |
| LiveBench Instruction Following | — | 58.1% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- Gemma 2 27B: 37.3 (#213)

| Benchmark | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1092 | 1231 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- Gemma 2 27B: 44.4 (#220)

| Benchmark | DeepSeek LLM 67B | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1105 | 1231 |
| LMArena Creative Writing | 1067 | 1241 |
| LMArena Multi-Turn | 1082 | 1224 |
| LiveBench Language | — | 32.6% |

## FAQ

### Is DeepSeek LLM 67B better than Gemma 2 27B?

Gemma 2 27B is the stronger model overall, scoring 29.2 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or Gemma 2 27B better for coding?

Gemma 2 27B scores higher on coding benchmarks: 33.5 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Gemma 2 27B share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemma 2 27B has 34.