# Gemma 4 31B IT vs Qwen-14B

> Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 31.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-qwen-14b
- Last updated: 2026-10-12
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Gemma 4 31B IT scores higher in 7 categories and Qwen-14B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.5 to 27.6.

## Snapshot

| | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 43.5 | 31.4 |
| Rank | 90 | 275 |
| Context | 262K | — |
| Input $/M | $0.09 | — |
| Output $/M | $0.34 | — |
| Weights | Open | Open |

## Coding

- Gemma 4 31B IT: 42.3 (#108)
- Qwen-14B: 31.2 (#288)

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| LMArena Coding | 1459 | 1071 |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |

## Reasoning

- Gemma 4 31B IT: 27.2 (#122)
- Qwen-14B: 19.6 (#257)

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1027 |
| Epoch Capabilities Index | 142.74 | 113.03 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |

## Math

- Gemma 4 31B IT: 43.2 (#81)
- Qwen-14B: 31.2 (#227)

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| LMArena Math | 1465 | 1068 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| GSM8K | — | 61.3% |

## Knowledge

- Gemma 4 31B IT: 37.9 (#151)
- Qwen-14B: —

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1465 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |

## Multimodal

- Gemma 4 31B IT: 41.6 (#34)
- Qwen-14B: —

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |

## Multilingual

- Gemma 4 31B IT: 53.8 (#57)
- Qwen-14B: 27.5 (#275)

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1431 | 1041 |
| LMArena Chinese | 1476 | 1077 |
| LMArena French | 1435 | — |
| LMArena Russian | 1460 | — |
| LMArena Spanish | 1444 | — |

## Instruction Following

- Gemma 4 31B IT: 75.5 (#61)
- Qwen-14B: 52.4 (#289)

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1031 |

## Long Context

- Gemma 4 31B IT: 44.2 (#71)
- Qwen-14B: 31.3 (#280)

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1446 | 1028 |

## Writing & Preference

- Gemma 4 31B IT: 60.5 (#96)
- Qwen-14B: 27.6 (#299)

| Benchmark | Gemma 4 31B IT | Qwen-14B |
|---|---|---|
| LMArena Text | 1443 | 1051 |
| LMArena Creative Writing | 1415 | 1028 |
| LMArena Multi-Turn | 1452 | 1022 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |

## FAQ

### Is Gemma 4 31B IT better than Qwen-14B?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 31.4 on the Noometry Index.

### Is Gemma 4 31B IT or Qwen-14B better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 31.2 in the Noometry coding category.

### How many benchmarks do Gemma 4 31B IT and Qwen-14B share?

11 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen-14B has 18.