# Gemma 3 12B vs Qwen3.6 Max Preview

> Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 32.1 on the Noometry Index. Gemma 3 12B costs 39× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-qwen3-6-max-preview
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 54.1 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 91.1% for Qwen3.6 Max Preview.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 131K.
- Gemma 3 12B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 32.1 | 51.5 |
| Rank | 262 | 43 |
| Context | 131K | 262K |
| Input $/M | $0.05 | $1.30 |
| Output $/M | $0.15 | $7.80 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 12B: 31.7 (#280)
- Qwen3.6 Max Preview: 48.7 (#54)

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1281 | 1471 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |
| SciCode | 17.4% | — |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- Qwen3.6 Max Preview: —

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
| Vending-Bench 2 | — | 4,254 |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- Qwen3.6 Max Preview: 41.7 (#53)

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| Chess Puzzles | 0% | 20% |
| LMArena Hard Prompts | 1309 | 1457 |
| DTBench | 48.8% | 87.2% |
| LMCA | 4.5% | 42.5% |
| Epoch Capabilities Index | 123.5 | 149.24 |
| SimpleBench | — | 63% |
| NYT Connections (extended) | — | 74.1% |
| CritPt | 0% | — |
| Mystery Game Puzzles | — | 19% |

## Math

- Gemma 3 12B: 22.3 (#279)
- Qwen3.6 Max Preview: 54.1 (#46)

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 91.1% |
| LMArena Math | 1307 | 1465 |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- Qwen3.6 Max Preview: 57.6 (#39)

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 39.5% | 87.4% |
| LMArena Expert | 1248 | 1478 |
| SimpleQA Verified | — | 52% |
| Vectara Hallucination Rate | 4.4% | — |

## Multimodal

- Gemma 3 12B: —
- Qwen3.6 Max Preview: —

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- Qwen3.6 Max Preview: 54.2 (#48)

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1318 | 1437 |
| LMArena Russian | 1335 | 1445 |
| LMArena Chinese | — | 1487 |
| LMArena French | — | 1449 |
| LMArena German | 1370 | — |
| LMArena Spanish | — | 1454 |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- Qwen3.6 Max Preview: 75.7 (#55)

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1299 | 1438 |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- Qwen3.6 Max Preview: 44.6 (#61)

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1317 | 1457 |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- Qwen3.6 Max Preview: 63.8 (#60)

| Benchmark | Gemma 3 12B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1334 | 1447 |
| LMArena Creative Writing | 1331 | 1435 |
| LMArena Multi-Turn | 1334 | 1456 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Qwen3.6 Max Preview?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 32.1 on the Noometry Index. Gemma 3 12B costs 39× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 12B or Qwen3.6 Max Preview?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.

### Is Gemma 3 12B or Qwen3.6 Max Preview better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 31.7 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.6 Max Preview does, with 262K tokens against 131K.

### How many benchmarks do Gemma 3 12B and Qwen3.6 Max Preview share?

17 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen3.6 Max Preview has 29.