# Gemma 3 12B vs Qwen-14B

> Gemma 3 12B is the stronger model overall, scoring 31.8 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Qwen-14B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 12B leads 47.7 to 27.8.

## Snapshot

| | Gemma 3 12B | Qwen-14B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 31.8 | 30.8 |
| Rank | 255 | 273 |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.2 (#276)
- Qwen-14B: 30.6 (#283)

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| LMArena Coding | 1281 | 1072 |
| SciCode | 17.4% | — |

## Agentic & Tool Use

- Gemma 3 12B: 25.3 (#101)
- Qwen-14B: —

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.2 (#307)
- Qwen-14B: 18.7 (#255)

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1027 |
| Epoch Capabilities Index | 123.49 | 112.8 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |

## Math

- Gemma 3 12B: 21.0 (#273)
- Qwen-14B: 28.7 (#224)

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| LMArena Math | 1307 | 1068 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| GSM8K | — | 61.3% |

## Knowledge

- Gemma 3 12B: 26.5 (#250)
- Qwen-14B: —

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |

## Multimodal

- Gemma 3 12B: —
- Qwen-14B: —

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.9 (#160)
- Qwen-14B: 27.7 (#270)

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1318 | 1042 |
| LMArena Chinese | — | 1077 |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |

## Instruction Following

- Gemma 3 12B: 68.8 (#179)
- Qwen-14B: 52.6 (#284)

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1031 |

## Long Context

- Gemma 3 12B: 40.0 (#157)
- Qwen-14B: 31.3 (#276)

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1317 | 1029 |

## Writing & Preference

- Gemma 3 12B: 47.7 (#205)
- Qwen-14B: 27.8 (#294)

| Benchmark | Gemma 3 12B | Qwen-14B |
|---|---|---|
| LMArena Text | 1334 | 1051 |
| LMArena Creative Writing | 1331 | 1028 |
| LMArena Multi-Turn | 1334 | 1022 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Qwen-14B?

Gemma 3 12B is the stronger model overall, scoring 31.8 to 30.8 on the Noometry Index.

### Is Gemma 3 12B or Qwen-14B better for coding?

They score almost the same on coding (31.2 vs 30.6); test both on your own repository before choosing.

### How many benchmarks do Gemma 3 12B and Qwen-14B share?

10 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen-14B has 18.