# Qwen-14B vs Qwen2-72B

> Qwen-14B is the stronger model overall, scoring 31.4 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen-14b-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Qwen-14B scores higher in 2 categories and Qwen2-72B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 40.8 to 27.6.

## Snapshot

| | Qwen-14B | Qwen2-72B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.4 | 30.0 |
| Rank | 275 | 300 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Qwen-14B: 31.2 (#288)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1071 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Qwen-14B: —
- Qwen2-72B: 17.0 (#146)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Qwen-14B: 19.6 (#257)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1191 |
| Epoch Capabilities Index | 113.03 | 125.28 |
| BIG-Bench Hard | 55% | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |

## Math

- Qwen-14B: 31.2 (#227)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1068 | 1235 |
| MATH Level 5 | — | 39.1% |
| GSM8K | 61.3% | — |

## Knowledge

- Qwen-14B: —
- Qwen2-72B: 21.2 (#275)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| MMLU | 66.3% | 82.4% |
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |

## Multilingual

- Qwen-14B: 27.5 (#275)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1041 | 1176 |
| LMArena Chinese | 1077 | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |

## Instruction Following

- Qwen-14B: 52.4 (#289)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1181 |

## Long Context

- Qwen-14B: 31.3 (#280)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1028 | 1192 |

## Writing & Preference

- Qwen-14B: 27.6 (#299)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Qwen-14B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1051 | 1203 |
| LMArena Creative Writing | 1028 | 1181 |
| LMArena Multi-Turn | 1022 | 1196 |

## FAQ

### Is Qwen-14B better than Qwen2-72B?

Qwen-14B is the stronger model overall, scoring 31.4 to 30.0 on the Noometry Index.

### Is Qwen-14B or Qwen2-72B better for coding?

Qwen-14B scores higher on coding benchmarks: 31.2 versus 29.1 in the Noometry coding category.

### How many benchmarks do Qwen-14B and Qwen2-72B share?

12 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen2-72B has 26.