# ERNIE 5.1 vs Qwen2.5-Coder-32B

> ERNIE 5.1 is the stronger model overall, scoring 43.1 to 32.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-qwen2-5-coder-32b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 41.8.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.1 | 32.9 |
| Rank | 87 | 239 |
| Context | — | 33K |
| Input $/M | — | $0.66 |
| Output $/M | — | $1 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 43.4 (#78)
- Qwen2.5-Coder-32B: 22.4 (#328)

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1488 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Agentic & Tool Use

- ERNIE 5.1: —
- Qwen2.5-Coder-32B: —

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- Qwen2.5-Coder-32B: 20.4 (#220)

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1251 |
| NYT Connections (extended) | 23.4% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.41 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- ERNIE 5.1: 37.5 (#96)
- Qwen2.5-Coder-32B: 30.8 (#203)

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1481 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- Qwen2.5-Coder-32B: 32.9 (#200)

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1491 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- Qwen2.5-Coder-32B: 38.0 (#230)

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1455 | 1205 |
| LMArena Chinese | 1507 | 1222 |
| LMArena Russian | 1459 | 1228 |
| LMArena French | 1486 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1428 | — |
| LMArena Spanish | 1472 | — |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- Qwen2.5-Coder-32B: 61.6 (#240)

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- Qwen2.5-Coder-32B: 37.9 (#204)

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1462 | 1251 |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- Qwen2.5-Coder-32B: 41.8 (#235)

| Benchmark | ERNIE 5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1468 | 1230 |
| LMArena Creative Writing | 1440 | 1174 |
| LMArena Multi-Turn | 1471 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is ERNIE 5.1 better than Qwen2.5-Coder-32B?

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 32.9 on the Noometry Index.

### Is ERNIE 5.1 or Qwen2.5-Coder-32B better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 22.4 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Qwen2.5-Coder-32B share?

12 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen2.5-Coder-32B has 31.