Model comparison
Hy3 vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 44.2 on the Noometry Index. Hy3 costs 9.9× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Tencent
StepFunSummary
- They share 14 benchmarks with published results for both. Hy3 scores higher in 0 categories and Step 5 Preview in 8 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 26.1.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Step 5 Preview | |
|---|---|---|
| Provider | Tencent | StepFun |
| Noometry Index | 44.2 | 47.9 |
| Released | 2026-07-06 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.02M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.0825 | $1 |
| Output $ / M tokens | $0.33 | $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
Hy3: 46.8 (#63), Step 5 Preview: 51.8 (#36)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1508 | 1564 |
| LMArena Coding | 1464 | 1480 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Hy3: 26.1 (#136), Step 5 Preview: 40.0 (#57)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1465 |
| NYT Connections (extended) | 41.2% | — |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
Hy3: 40.1 (#93), Step 5 Preview: 46.1 (#72)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1475 | 1470 |
| ProofBench | — | 42% |
Knowledge Too close to call
Hy3: 40.8 (#114), Step 5 Preview: 41.2 (#112)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1460 | 1470 |
Multimodal Not comparable
Hy3: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Too close to call
Hy3: 53.5 (#65), Step 5 Preview: 53.8 (#54)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1426 | 1432 |
| LMArena Chinese | 1493 | 1519 |
| LMArena Russian | 1432 | 1436 |
| LMArena Spanish | 1456 | 1439 |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
Instruction Following Too close to call
Hy3: 75.1 (#70), Step 5 Preview: 76.0 (#50)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1426 | 1444 |
Long Context Too close to call
Hy3: 44.1 (#75), Step 5 Preview: 44.5 (#64)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1442 | 1455 |
Writing & Preference Too close to call
Hy3: 62.2 (#81), Step 5 Preview: 62.8 (#71)
| Benchmark | Hy3 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1439 | 1442 |
| LMArena Creative Writing | 1402 | 1410 |
| LMArena Multi-Turn | 1436 | 1447 |
Frequently asked questions
Is Hy3 better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 44.2 on the Noometry Index. Hy3 costs 9.9× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Hy3 or Step 5 Preview?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Hy3 or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 262K.
How many benchmarks do Hy3 and Step 5 Preview share?
14 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Step 5 Preview has 18.