Model comparison
ERNIE 5.1 vs Step 3.5 Flash
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 42.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
Baidu
StepFunSummary
- They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 6 categories and Step 3.5 Flash in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 58.8.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Step 3.5 Flash | |
|---|---|---|
| Provider | Baidu | StepFun |
| Noometry Index | 43.8 | 42.3 |
| Released | — | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 19 | 19 |
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 3.5 Flash: 42.4 (#105)
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1488 | 1436 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Step 3.5 Flash: —
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Too close to call
ERNIE 5.1: 21.9 (#211), Step 3.5 Flash: 22.2 (#202)
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 23.4% | 28.4% |
| LMArena Hard Prompts | 1481 | 1411 |
Math Step 3.5 Flash leads
ERNIE 5.1: 40.3 (#92), Step 3.5 Flash: 42.6 (#84)
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1481 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Step 3.5 Flash: 39.6 (#132)
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1492 | 1421 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Step 3.5 Flash: 50.5 (#119)
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1454 | 1385 |
| LMArena Chinese | 1508 | 1447 |
| LMArena French | 1488 | 1421 |
| LMArena German | 1470 | 1405 |
| LMArena Japanese | 1422 | 1354 |
| LMArena Korean | 1427 | 1352 |
| LMArena Russian | 1459 | 1385 |
| LMArena Spanish | 1473 | 1419 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Step 3.5 Flash: 73.1 (#124)
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1460 | 1385 |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Step 3.5 Flash: 42.8 (#117)
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1462 | 1402 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Step 3.5 Flash: 58.8 (#113)
| Benchmark | ERNIE 5.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1468 | 1403 |
| LMArena Creative Writing | 1441 | 1357 |
| LMArena Multi-Turn | 1471 | 1405 |
Frequently asked questions
Is ERNIE 5.1 better than Step 3.5 Flash?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 42.3 on the Noometry Index.
Is ERNIE 5.1 or Step 3.5 Flash better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 42.4 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Step 3.5 Flash share?
18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Step 3.5 Flash has 19.