# ERNIE 5.0 0110 vs Step 3

> ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-0-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 8 categories and Step 3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 27.6 to 16.3.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| Provider | Baidu | StepFun |
| Noometry Index | 41.2 | 39.9 |
| Rank | 129 | 145 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.0 0110: 42.3 (#94)
- Step 3: 39.5 (#144)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Coding | 1455 | 1367 |

## Reasoning

- ERNIE 5.0 0110: 16.3 (#296)
- Step 3: 27.6 (#102)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1446 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 10.3% | — |
| Thematic Generalization | 41.7% | — |

## Math

- ERNIE 5.0 0110: 36.5 (#111)
- Step 3: 34.9 (#148)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Math | 1437 | 1366 |

## Knowledge

- ERNIE 5.0 0110: 39.2 (#125)
- Step 3: 36.2 (#161)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Expert | 1427 | 1333 |

## Multimodal

- ERNIE 5.0 0110: 39.1 (#49)
- Step 3: 34.9 (#81)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Vision | 1248 | 1176 |

## Multilingual

- ERNIE 5.0 0110: 54.3 (#47)
- Step 3: 46.5 (#154)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Non-English | 1436 | 1327 |
| LMArena Chinese | 1512 | 1396 |
| LMArena German | 1462 | 1371 |
| LMArena Korean | 1406 | 1271 |
| LMArena Russian | 1446 | 1331 |
| LMArena Spanish | 1473 | 1372 |
| LMArena French | 1466 | — |
| LMArena Japanese | 1383 | — |

## Instruction Following

- ERNIE 5.0 0110: 74.7 (#88)
- Step 3: 70.6 (#159)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1413 | 1332 |

## Long Context

- ERNIE 5.0 0110: 43.4 (#90)
- Step 3: 40.3 (#152)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1326 |

## Writing & Preference

- ERNIE 5.0 0110: 63.4 (#64)
- Step 3: 54.5 (#146)

| Benchmark | ERNIE 5.0 0110 | Step 3 |
|---|---|---|
| LMArena Text | 1445 | 1351 |
| LMArena Creative Writing | 1426 | 1322 |
| LMArena Multi-Turn | 1433 | 1340 |

## FAQ

### Is ERNIE 5.0 0110 better than Step 3?

ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 39.9 on the Noometry Index.

### Is ERNIE 5.0 0110 or Step 3 better for coding?

ERNIE 5.0 0110 scores higher on coding benchmarks: 42.3 versus 39.5 in the Noometry coding category.

### How many benchmarks do ERNIE 5.0 0110 and Step 3 share?

16 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and Step 3 has 17.