Model comparison
ERNIE 5.1 vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 43.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Baidu
StepFunSummary
- They share 13 benchmarks with published results for both. ERNIE 5.1 scores higher in 5 categories and Step 5 Preview in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 21.9.
Side by side
| ERNIE 5.1 | Step 5 Preview | |
|---|---|---|
| Provider | Baidu | StepFun |
| Noometry Index | 43.8 | 47.9 |
| Released | — | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 19 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
ERNIE 5.1: 44.0 (#76), Step 5 Preview: 51.8 (#36)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1488 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Step 5 Preview: —
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Step 5 Preview leads
ERNIE 5.1: 21.9 (#211), Step 5 Preview: 40.0 (#57)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1465 |
| NYT Connections (extended) | 23.4% | — |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
ERNIE 5.1: 40.3 (#92), Step 5 Preview: 46.1 (#72)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1481 | 1470 |
| ProofBench | — | 42% |
Knowledge Too close to call
ERNIE 5.1: 41.9 (#102), Step 5 Preview: 41.2 (#112)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1492 | 1470 |
Multimodal Not comparable
ERNIE 5.1: —, Step 5 Preview: 41.0 (#41)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Step 5 Preview: 53.8 (#54)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1454 | 1432 |
| LMArena Chinese | 1508 | 1519 |
| LMArena Russian | 1459 | 1436 |
| LMArena Spanish | 1473 | 1439 |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
Instruction Following Too close to call
ERNIE 5.1: 76.7 (#37), Step 5 Preview: 76.0 (#50)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1460 | 1444 |
Long Context Too close to call
ERNIE 5.1: 44.7 (#59), Step 5 Preview: 44.5 (#64)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1462 | 1455 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Step 5 Preview: 62.8 (#71)
| Benchmark | ERNIE 5.1 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1468 | 1442 |
| LMArena Creative Writing | 1441 | 1410 |
| LMArena Multi-Turn | 1471 | 1447 |
Frequently asked questions
Is ERNIE 5.1 better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 43.8 on the Noometry Index.
Is ERNIE 5.1 or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 44.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Step 5 Preview share?
13 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Step 5 Preview has 18.