# Gemma 3 12B vs Qwen1.5-72B

> Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-qwen1-5-72b
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Qwen1.5-72B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 3 12B leads 26.5 to 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 39.5% for Gemma 3 12B and 28.8% for Qwen1.5-72B.

## Snapshot

| | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 32.1 | 30.8 |
| Rank | 262 | 285 |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.7 (#280)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1281 | 1165 |
| SciCode | 17.4% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- Qwen1.5-72B: —

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1148 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |

## Math

- Gemma 3 12B: 22.3 (#279)
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1307 | 1164 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 39.5% | 28.8% |
| LMArena Expert | 1248 | 1136 |
| Vectara Hallucination Rate | 4.4% | — |

## Multimodal

- Gemma 3 12B: —
- Qwen1.5-72B: —

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1318 | 1135 |
| LMArena German | 1370 | 1084 |
| LMArena Russian | 1335 | 1104 |
| LMArena Chinese | — | 1186 |
| LMArena French | — | 1159 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Spanish | — | 1110 |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1141 |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1317 | 1157 |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | Gemma 3 12B | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1334 | 1166 |
| LMArena Creative Writing | 1331 | 1137 |
| LMArena Multi-Turn | 1334 | 1160 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Qwen1.5-72B?

Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.

### Is Gemma 3 12B or Qwen1.5-72B better for coding?

They score almost the same on coding (31.7 vs 31.9); test both on your own repository before choosing.

### How many benchmarks do Gemma 3 12B and Qwen1.5-72B share?

13 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen1.5-72B has 22.