# Gemma 4 31B IT vs Qwen1.5-32B

> Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-qwen1-5-32b
- Last updated: 2026-10-12
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.5 to 34.2.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for Gemma 4 31B IT and 30.7% for Qwen1.5-32B.

## Snapshot

| | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 43.5 | 30.5 |
| Rank | 90 | 293 |
| Context | 262K | — |
| Input $/M | $0.09 | — |
| Output $/M | $0.34 | — |
| Weights | Open | Open |

## Coding

- Gemma 4 31B IT: 42.3 (#108)
- Qwen1.5-32B: 31.7 (#282)

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1459 | 1155 |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 925.5 | — |

## Reasoning

- Gemma 4 31B IT: 27.2 (#122)
- Qwen1.5-32B: 21.8 (#212)

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1130 |
| 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% | — |
| Epoch Capabilities Index | 142.74 | — |

## Math

- Gemma 4 31B IT: 43.2 (#81)
- Qwen1.5-32B: 33.0 (#207)

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1465 | 1155 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |

## Knowledge

- Gemma 4 31B IT: 37.9 (#151)
- Qwen1.5-32B: 13.5 (#296)

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 75.8% | 30.7% |
| LMArena Expert | 1465 | 1126 |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| MMLU | — | 74.4% |

## Multimodal

- Gemma 4 31B IT: 41.6 (#34)
- Qwen1.5-32B: —

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |

## Multilingual

- Gemma 4 31B IT: 53.8 (#57)
- Qwen1.5-32B: 31.4 (#259)

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1431 | 1106 |
| LMArena Chinese | 1476 | 1177 |
| LMArena French | 1435 | 1101 |
| LMArena Russian | 1460 | 1073 |
| LMArena Spanish | 1444 | 1089 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1008 |

## Instruction Following

- Gemma 4 31B IT: 75.5 (#61)
- Qwen1.5-32B: 57.7 (#265)

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1116 |

## Long Context

- Gemma 4 31B IT: 44.2 (#71)
- Qwen1.5-32B: 34.7 (#246)

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1446 | 1146 |

## Writing & Preference

- Gemma 4 31B IT: 60.5 (#96)
- Qwen1.5-32B: 34.2 (#271)

| Benchmark | Gemma 4 31B IT | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1443 | 1137 |
| LMArena Creative Writing | 1415 | 1083 |
| LMArena Multi-Turn | 1452 | 1140 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |

## FAQ

### Is Gemma 4 31B IT better than Qwen1.5-32B?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 30.5 on the Noometry Index.

### Is Gemma 4 31B IT or Qwen1.5-32B better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 31.7 in the Noometry coding category.

### How many benchmarks do Gemma 4 31B IT and Qwen1.5-32B share?

15 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Qwen1.5-32B has 21.