Model comparison
ERNIE 5.1 vs Step 3
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 40.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
Baidu
StepFunSummary
- They share 15 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Step 3 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 54.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Step 3 | |
|---|---|---|
| Provider | Baidu | StepFun |
| Noometry Index | 43.8 | 40.5 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
ERNIE 5.1: 44.0 (#76), Step 3: 40.1 (#147)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Coding | 1488 | 1367 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Step 3: —
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Step 3 leads
ERNIE 5.1: 21.9 (#211), Step 3: 28.4 (#105)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 23.4% | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Step 3: 37.6 (#148)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Math | 1481 | 1366 |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Step 3: 36.8 (#164)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Expert | 1492 | 1333 |
Multimodal Not comparable
ERNIE 5.1: —, Step 3: 35.5 (#86)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Step 3: 46.3 (#159)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Non-English | 1454 | 1327 |
| LMArena Chinese | 1508 | 1397 |
| LMArena German | 1470 | 1371 |
| LMArena Korean | 1427 | 1269 |
| LMArena Russian | 1459 | 1331 |
| LMArena Spanish | 1473 | 1371 |
| LMArena French | 1488 | — |
| LMArena Japanese | 1422 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Step 3: 70.4 (#164)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1332 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Step 3: 40.3 (#157)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1462 | 1326 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Step 3: 54.3 (#151)
| Benchmark | ERNIE 5.1 | Step 3 |
|---|---|---|
| LMArena Text | 1468 | 1350 |
| LMArena Creative Writing | 1441 | 1321 |
| LMArena Multi-Turn | 1471 | 1341 |
Frequently asked questions
Is ERNIE 5.1 better than Step 3?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 40.5 on the Noometry Index.
Is ERNIE 5.1 or Step 3 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 40.1 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Step 3 share?
15 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Step 3 has 17.