# Gemma 3 1B vs Qwen2.5 72B Instruct

> Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 20.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-1b-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Gemma 3 1B scores higher in 0 categories and Qwen2.5 72B Instruct in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5 72B Instruct leads 26.9 to 7.1.
- The biggest single-benchmark swing is GPQA Diamond: 19.9% for Gemma 3 1B and 49.1% for Qwen2.5 72B Instruct.

## Snapshot

| | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 20.7 | 31.5 |
| Rank | 348 | 259 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Open | Open |

## Coding

- Gemma 3 1B: —
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1293 |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Gemma 3 1B: 13.5 (#144)
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 7.2% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Gemma 3 1B: 18.5 (#260)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1271 |
| 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 3 1B: 9.6 (#310)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Gemma 3 1B: 7.1 (#309)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 19.9% | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Gemma 3 1B: —
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1255 |

## Instruction Following

- Gemma 3 1B: —
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |

## Long Context

- Gemma 3 1B: —
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |

## Writing & Preference

- Gemma 3 1B: —
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | Gemma 3 1B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |

## FAQ

### Is Gemma 3 1B better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 20.7 on the Noometry Index.

### How many benchmarks do Gemma 3 1B and Qwen2.5 72B Instruct share?

2 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and Qwen2.5 72B Instruct has 43.