# Gemma 3n E4b IT vs Qwen2.5 72B Instruct

> Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3n-e4b-it-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 6 categories and Qwen2.5 72B Instruct in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 3n E4b IT leads 32.5 to 18.1.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 33K.

## Snapshot

| | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 36.7 | 31.5 |
| Rank | 203 | 259 |
| Context | 33K | 131K |
| Input $/M | $0.06 | $1.40 |
| Output $/M | $0.12 | $5.60 |
| Weights | Open | Open |

## Coding

- Gemma 3n E4b IT: 36.4 (#193)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1269 | 1293 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Gemma 3n E4b IT: —
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Gemma 3n E4b IT: 19.2 (#239)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1271 |
| Kagi LLM Benchmark | 31.5% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Gemma 3n E4b IT: 32.5 (#186)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1251 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Gemma 3n E4b IT: 33.6 (#193)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1245 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Gemma 3n E4b IT: 43.5 (#179)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1285 | 1252 |
| LMArena Chinese | 1310 | 1272 |
| LMArena French | 1330 | 1279 |
| LMArena German | 1312 | 1234 |
| LMArena Japanese | 1274 | 1180 |
| LMArena Korean | 1259 | 1188 |
| LMArena Russian | 1288 | 1264 |
| LMArena Spanish | 1305 | 1255 |

## Instruction Following

- Gemma 3n E4b IT: 66.3 (#205)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1255 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Gemma 3n E4b IT: 38.8 (#185)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1277 | 1282 |

## Writing & Preference

- Gemma 3n E4b IT: 50.3 (#181)
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | Gemma 3n E4b IT | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1306 | 1269 |
| LMArena Creative Writing | 1287 | 1221 |
| LMArena Multi-Turn | 1276 | 1272 |
| WildBench | — | 80.2% |

## FAQ

### Is Gemma 3n E4b IT better than Qwen2.5 72B Instruct?

Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 31.5 on the Noometry Index.

### Which is cheaper, Gemma 3n E4b IT or Qwen2.5 72B Instruct?

Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

### Is Gemma 3n E4b IT or Qwen2.5 72B Instruct better for coding?

Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 32.8 in the Noometry coding category.

### Which has the bigger context window?

Qwen2.5 72B Instruct does, with 131K tokens against 33K.

### How many benchmarks do Gemma 3n E4b IT and Qwen2.5 72B Instruct share?

17 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Qwen2.5 72B Instruct has 43.