# Gemma 7B vs Qwen3.8 27B

> Qwen3.8 27B is the stronger model overall, scoring 45.3 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-7b-vs-qwen3-8-27b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.9 to 27.2.

## Snapshot

| | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 29.5 | 45.3 |
| Rank | 295 | 64 |
| Context | — | 262K |
| Input $/M | — | $0.99 |
| Output $/M | — | $1.49 |
| Weights | Open | Open |

## Coding

- Gemma 7B: 29.9 (#290)
- Qwen3.8 27B: 50.3 (#42)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1048 | 1487 |
| LMArena WebDev | — | 1592 |
| SciCode | — | 46.6% |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |

## Reasoning

- Gemma 7B: 19.0 (#247)
- Qwen3.8 27B: 31.5 (#71)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1459 |
| Epoch Capabilities Index | 111.74 | 149.38 |
| NYT Connections (extended) | — | 54.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |

## Math

- Gemma 7B: 28.7 (#225)
- Qwen3.8 27B: 35.7 (#139)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1066 | 1453 |
| ProofBench | — | 16% |
| GSM8K | 46.4% | — |

## Knowledge

- Gemma 7B: 26.8 (#248)
- Qwen3.8 27B: 40.9 (#105)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1002 | 1482 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |

## Multimodal

- Gemma 7B: —
- Qwen3.8 27B: 40.5 (#36)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1270 |

## Multilingual

- Gemma 7B: 25.3 (#282)
- Qwen3.8 27B: 54.0 (#54)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 999 | 1431 |
| LMArena Chinese | 1035 | 1504 |
| LMArena French | 1024 | 1468 |
| LMArena Russian | 993 | 1421 |
| LMArena German | — | 1435 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1389 |
| LMArena Spanish | — | 1444 |

## Instruction Following

- Gemma 7B: 51.7 (#290)
- Qwen3.8 27B: 75.8 (#54)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1017 | 1436 |

## Long Context

- Gemma 7B: 31.1 (#277)
- Qwen3.8 27B: 44.3 (#66)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1022 | 1448 |

## Writing & Preference

- Gemma 7B: 27.2 (#297)
- Qwen3.8 27B: 65.9 (#41)

| Benchmark | Gemma 7B | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1056 | 1441 |
| LMArena Creative Writing | 1024 | 1382 |
| LMArena Multi-Turn | 963 | 1443 |
| EQ-Bench Creative Writing | — | 1671 |

## FAQ

### Is Gemma 7B better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 45.3 to 29.5 on the Noometry Index.

### Is Gemma 7B or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 29.9 in the Noometry coding category.

### How many benchmarks do Gemma 7B and Qwen3.8 27B share?

14 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Qwen3.8 27B has 28.