# Qwen1.5-72B vs Qwen2.5-Coder-32B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen1-5-72b-vs-qwen2-5-coder-32b
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Qwen1.5-72B scores higher in 2 categories and Qwen2.5-Coder-32B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Coder-32B leads 33.4 to 11.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 40.3% for Qwen1.5-72B and 58% for Qwen2.5-Coder-32B.

## Snapshot

| | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | 33.4 |
| Rank | 285 | 245 |
| Context | — | 33K |
| Input $/M | — | $0.66 |
| Output $/M | — | $1 |
| Weights | Open | Open |

## Coding

- Qwen1.5-72B: 31.9 (#277)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 33.2% | 49% |
| LMArena Coding | 1165 | 1276 |
| BigCodeBench Complete | 40.3% | 58% |
| HumanEval+ | 59.1% | 87.2% |
| MBPP+ | 61.6% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LiveBench Coding | — | 56.9% |

## Reasoning

- Qwen1.5-72B: 22.2 (#203)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1148 | 1251 |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- Qwen1.5-72B: 33.2 (#205)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1164 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- Qwen1.5-72B: 11.5 (#300)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1136 | 1221 |
| GPQA Diamond | 28.8% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- Qwen1.5-72B: 33.2 (#253)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1135 | 1205 |
| LMArena Chinese | 1186 | 1222 |
| LMArena Russian | 1104 | 1228 |
| LMArena French | 1159 | — |
| LMArena German | 1084 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1050 | — |
| LMArena Spanish | 1110 | — |

## Instruction Following

- Qwen1.5-72B: 59.3 (#256)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1141 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Qwen1.5-72B: 35.1 (#243)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1157 | 1251 |

## Writing & Preference

- Qwen1.5-72B: 37.3 (#258)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | Qwen1.5-72B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1166 | 1230 |
| LMArena Creative Writing | 1137 | 1174 |
| LMArena Multi-Turn | 1160 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Qwen1.5-72B better than Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 30.8 on the Noometry Index.

### Is Qwen1.5-72B or Qwen2.5-Coder-32B better for coding?

Qwen1.5-72B scores higher on coding benchmarks: 31.9 versus 22.6 in the Noometry coding category.

### How many benchmarks do Qwen1.5-72B and Qwen2.5-Coder-32B share?

16 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Qwen2.5-Coder-32B has 31.