# Qwen1.5-7B vs Qwen2-72B

> Qwen1.5-7B is the stronger model overall, scoring 31.4 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen1-5-7b-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Qwen1.5-7B scores higher in 3 categories and Qwen2-72B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 40.8 to 29.6.

## Snapshot

| | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.4 | 30.0 |
| Rank | 273 | 300 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Qwen1.5-7B: 32.2 (#276)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1107 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Qwen1.5-7B: —
- Qwen2-72B: 17.0 (#146)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Qwen1.5-7B: 20.4 (#240)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1065 | 1191 |
| Epoch Capabilities Index | — | 125.28 |

## Math

- Qwen1.5-7B: 31.4 (#224)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1080 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Qwen1.5-7B: 28.7 (#243)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1055 | 1171 |
| MMLU | 62.6% | 82.4% |
| GPQA Diamond | — | 40.8% |

## Multilingual

- Qwen1.5-7B: 28.5 (#271)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1058 | 1176 |
| LMArena Chinese | 1141 | 1240 |
| LMArena Russian | 1006 | 1169 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1169 |

## Instruction Following

- Qwen1.5-7B: 54.1 (#281)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1058 | 1181 |

## Long Context

- Qwen1.5-7B: 33.1 (#266)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1090 | 1192 |

## Writing & Preference

- Qwen1.5-7B: 29.6 (#293)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Qwen1.5-7B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1083 | 1203 |
| LMArena Creative Writing | 1035 | 1181 |
| LMArena Multi-Turn | 1062 | 1196 |

## FAQ

### Is Qwen1.5-7B better than Qwen2-72B?

Qwen1.5-7B is the stronger model overall, scoring 31.4 to 30.0 on the Noometry Index.

### Is Qwen1.5-7B or Qwen2-72B better for coding?

Qwen1.5-7B scores higher on coding benchmarks: 32.2 versus 29.1 in the Noometry coding category.

### How many benchmarks do Qwen1.5-7B and Qwen2-72B share?

13 benchmarks have published results for both models. Qwen1.5-7B has 13 scored results on Noometry and Qwen2-72B has 26.