# ERNIE 5.1 vs Qwen3-Coder 480B-A35B Instruct

> ERNIE 5.1 is the stronger model overall, scoring 43.8 to 38.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-qwen3-coder-480b-a35b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Qwen3-Coder 480B-A35B Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 55.3.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | Baidu | Alibaba (Qwen) |
| Noometry Index | 43.8 | 38.1 |
| Rank | 83 | 190 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 44.0 (#76)
- Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Coding | 1488 | 1412 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |

## Agentic & Tool Use

- ERNIE 5.1: —
- Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 21.9 (#211)
- Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| NYT Connections (extended) | 23.4% | — |

## Math

- ERNIE 5.1: 40.3 (#92)
- Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1481 | 1365 |

## Knowledge

- ERNIE 5.1: 41.9 (#102)
- Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1492 | 1338 |

## Multilingual

- ERNIE 5.1: 55.5 (#29)
- Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1454 | 1346 |
| LMArena Chinese | 1508 | 1357 |
| LMArena French | 1488 | 1398 |
| LMArena German | 1470 | 1325 |
| LMArena Japanese | 1422 | 1310 |
| LMArena Korean | 1427 | 1305 |
| LMArena Russian | 1459 | 1366 |
| LMArena Spanish | 1473 | 1360 |

## Instruction Following

- ERNIE 5.1: 76.7 (#37)
- Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1460 | 1355 |

## Long Context

- ERNIE 5.1: 44.7 (#59)
- Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1462 | 1378 |

## Writing & Preference

- ERNIE 5.1: 65.1 (#52)
- Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)

| Benchmark | ERNIE 5.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1468 | 1357 |
| LMArena Creative Writing | 1441 | 1333 |
| LMArena Multi-Turn | 1471 | 1365 |

## FAQ

### Is ERNIE 5.1 better than Qwen3-Coder 480B-A35B Instruct?

ERNIE 5.1 is the stronger model overall, scoring 43.8 to 38.1 on the Noometry Index.

### Is ERNIE 5.1 or Qwen3-Coder 480B-A35B Instruct better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 35.5 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Qwen3-Coder 480B-A35B Instruct share?

17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.