# Gemma 3 12B vs Qwen1.5-110B

> Qwen1.5-110B is the stronger model overall, scoring 34.2 to 32.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-qwen1-5-110b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 4 categories and Qwen1.5-110B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.7 to 33.6.

## Snapshot

| | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 32.1 | 34.2 |
| Rank | 262 | 234 |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.7 (#280)
- Qwen1.5-110B: 33.0 (#264)

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1281 | 1184 |
| SciCode | 17.4% | — |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- Qwen1.5-110B: —

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- Qwen1.5-110B: 22.7 (#189)

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1168 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
| ForecastBench | — | 57.7 |

## Math

- Gemma 3 12B: 22.3 (#279)
- Qwen1.5-110B: 33.7 (#201)

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1307 | 1185 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- Qwen1.5-110B: 31.2 (#219)

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1248 | 1144 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |

## Multimodal

- Gemma 3 12B: —
- Qwen1.5-110B: —

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- Qwen1.5-110B: 33.6 (#250)

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1318 | 1142 |
| LMArena German | 1370 | 1123 |
| LMArena Russian | 1335 | 1118 |
| LMArena Chinese | — | 1206 |
| LMArena French | — | 1151 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
| LMArena Spanish | — | 1142 |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- Qwen1.5-110B: 60.3 (#252)

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1158 |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- Qwen1.5-110B: 35.1 (#242)

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1317 | 1157 |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- Qwen1.5-110B: 38.0 (#255)

| Benchmark | Gemma 3 12B | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1334 | 1175 |
| LMArena Creative Writing | 1331 | 1148 |
| LMArena Multi-Turn | 1334 | 1160 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Qwen1.5-110B?

Qwen1.5-110B is the stronger model overall, scoring 34.2 to 32.1 on the Noometry Index.

### Is Gemma 3 12B or Qwen1.5-110B better for coding?

Qwen1.5-110B scores higher on coding benchmarks: 33.0 versus 31.7 in the Noometry coding category.

### How many benchmarks do Gemma 3 12B and Qwen1.5-110B share?

12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen1.5-110B has 20.