# Gemma 2B vs Qwen2.5 72B Instruct

> Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 29.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2b-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemma 2B scores higher in 1 category and Qwen2.5 72B Instruct in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.7 to 24.0.

## Snapshot

| | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 29.6 | 31.9 |
| Rank | 307 | 267 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Open | Open |

## Coding

- Gemma 2B: 29.4 (#305)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1010 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |

## Agentic & Tool Use

- Gemma 2B: —
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Gemma 2B: 18.8 (#275)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 989 | 1271 |
| BIG-Bench Hard | 35.2% | 79.8% |
| Epoch Capabilities Index | 94.2 | 129 |
| HellaSwag | 71.4% | 84.8% |
| PIQA | 77.3% | 82.6% |
| WinoGrande | 65.4% | 82.3% |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| ForecastBench | — | 57.5 |

## Math

- Gemma 2B: 30.0 (#239)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1009 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
| GSM8K | 17.7% | — |

## Knowledge

- Gemma 2B: —
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | 94.5% |
| MMLU | 42.3% | 85.3% |
| TriviaQA | 53.2% | 71.9% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| BoolQ | 69.4% | — |

## Multilingual

- Gemma 2B: 23.0 (#294)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 958 | 1252 |
| LMArena Chinese | 986 | 1272 |
| LMArena Russian | 937 | 1264 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1256 |

## Instruction Following

- Gemma 2B: 48.5 (#302)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 970 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Gemma 2B: 29.9 (#291)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 981 | 1282 |

## Writing & Preference

- Gemma 2B: 24.0 (#308)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Gemma 2B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1002 | 1269 |
| LMArena Creative Writing | 987 | 1221 |
| LMArena Multi-Turn | 945 | 1272 |
| WildBench | — | 80.2% |

## FAQ

### Is Gemma 2B better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 29.6 on the Noometry Index.

### Is Gemma 2B or Qwen2.5 72B Instruct better for coding?

Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 29.4 in the Noometry coding category.

### How many benchmarks do Gemma 2B and Qwen2.5 72B Instruct share?

19 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Qwen2.5 72B Instruct has 43.