Model comparison
Hy4 preview vs Step 3
Hy4 preview is the stronger model overall, scoring 45.3 to 40.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
StepFunSummary
- The widest gap is in math, where Hy4 preview leads 55.7 to 37.6.
Side by side
| Hy4 preview | Step 3 | |
|---|---|---|
| Provider | Tencent | StepFun |
| Noometry Index | 45.3 | 40.5 |
| Released | 2026-08-28 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.83 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 3 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Step 3: 40.1 (#147)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 1367 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Step 3: 28.4 (#105)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1355 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Step 3: 37.6 (#148)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1366 |
Knowledge Not comparable
Hy4 preview: —, Step 3: 36.8 (#164)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Hy4 preview: —, Step 3: 35.5 (#86)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Not comparable
Hy4 preview: —, Step 3: 46.3 (#159)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |
Instruction Following Not comparable
Hy4 preview: —, Step 3: 70.4 (#164)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Hy4 preview: —, Step 3: 40.3 (#157)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Hy4 preview: —, Step 3: 54.3 (#151)
| Benchmark | Hy4 preview | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is Hy4 preview better than Step 3?
Hy4 preview is the stronger model overall, scoring 45.3 to 40.5 on the Noometry Index.
Is Hy4 preview or Step 3 better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 40.1 in the Noometry coding category.
How many benchmarks do Hy4 preview and Step 3 share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Step 3 has 17.