# Gemma 3 12B vs QwQ-32B

> QwQ-32B is the stronger model overall, scoring 39.4 to 31.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-qwq-32b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and QwQ-32B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 36.2 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 59.2% for QwQ-32B.

## Snapshot

| | Gemma 3 12B | QwQ-32B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 31.8 | 39.4 |
| Rank | 255 | 153 |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.2 (#276)
- QwQ-32B: 34.9 (#220)

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| LMArena Coding | 1281 | 1333 |
| Aider Polyglot | — | 20.9% |
| SciCode | 17.4% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |

## Agentic & Tool Use

- Gemma 3 12B: 25.3 (#101)
- QwQ-32B: —

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.2 (#307)
- QwQ-32B: 22.9 (#171)

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1309 | 1326 |
| Epoch Capabilities Index | 123.49 | 137.6 |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 48.8% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 4.5% | — |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |

## Math

- Gemma 3 12B: 21.0 (#273)
- QwQ-32B: 36.2 (#123)

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 59.2% |
| LMArena Math | 1307 | 1359 |
| LiveBench Math | — | 77.8% |

## Knowledge

- Gemma 3 12B: 26.5 (#250)
- QwQ-32B: 37.2 (#150)

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 39.5% | 65.3% |
| LMArena Expert | 1248 | 1323 |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 4.4% | — |

## Multimodal

- Gemma 3 12B: —
- QwQ-32B: —

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.9 (#160)
- QwQ-32B: 45.0 (#171)

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1318 | 1306 |
| LMArena German | 1370 | 1313 |
| LMArena Russian | 1335 | 1297 |
| LMArena Chinese | — | 1378 |
| LMArena French | — | 1337 |
| LMArena Japanese | — | 1263 |
| LMArena Korean | — | 1278 |
| LMArena Spanish | — | 1353 |

## Instruction Following

- Gemma 3 12B: 68.8 (#179)
- QwQ-32B: 72.8 (#131)

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1297 |
| LiveBench Instruction Following | — | 81.8% |

## Long Context

- Gemma 3 12B: 40.0 (#157)
- QwQ-32B: 49.0 (#11)

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1317 | 1308 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- Gemma 3 12B: 47.7 (#205)
- QwQ-32B: 50.9 (#175)

| Benchmark | Gemma 3 12B | QwQ-32B |
|---|---|---|
| LMArena Text | 1334 | 1329 |
| LMArena Creative Writing | 1331 | 1288 |
| EQ-Bench Creative Writing | 1126 | 1257 |
| LMArena Multi-Turn | 1334 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| LiveBench Language | — | 51.4% |

## FAQ

### Is Gemma 3 12B better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.4 to 31.8 on the Noometry Index.

### Is Gemma 3 12B or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 34.9 versus 31.2 in the Noometry coding category.

### How many benchmarks do Gemma 3 12B and QwQ-32B share?

17 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and QwQ-32B has 36.