Model comparison
Hy4 preview vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 45.3 on the Noometry Index.
Last verified . 2 shared benchmarks.
Tencent
StepFunSummary
- They share 2 benchmarks with published results for both. Hy4 preview scores higher in 1 category and Step 5 Preview in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 55.7 to 46.1.
- The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 42% for Step 5 Preview.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Hy4 preview accepts more context: 1.05M tokens versus 1.02M.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Hy4 preview | Step 5 Preview | |
|---|---|---|
| Provider | Tencent | StepFun |
| Noometry Index | 45.3 | 47.9 |
| Released | 2026-08-28 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1.02M |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.75 | $1 |
| Output $ / M tokens | $2.25 | $2.70 |
| Results tracked | 3 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Hy4 preview: 51.6 (#38), Step 5 Preview: 51.8 (#36)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1632 | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
Reasoning Step 5 Preview leads
Hy4 preview: 31.9 (#79), Step 5 Preview: 40.0 (#57)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| CritPt | — | 20.9% |
| LMArena Hard Prompts | — | 1465 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Step 5 Preview: 46.1 (#72)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| ProofBench | 75% | 42% |
| LMArena Math | — | 1470 |
Knowledge Not comparable
Hy4 preview: —, Step 5 Preview: 41.2 (#112)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
Multimodal Not comparable
Hy4 preview: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
Hy4 preview: —, Step 5 Preview: 53.8 (#54)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
Hy4 preview: —, Step 5 Preview: 76.0 (#50)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
Hy4 preview: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Hy4 preview: —, Step 5 Preview: 62.8 (#71)
| Benchmark | Hy4 preview | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Hy4 preview better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 45.3 on the Noometry Index.
Which is cheaper, Hy4 preview or Step 5 Preview?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Hy4 preview or Step 5 Preview better for coding?
They score almost the same on coding (51.6 vs 51.8); test both on your own repository before choosing.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 1.02M.
How many benchmarks do Hy4 preview and Step 5 Preview share?
2 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Step 5 Preview has 18.