# Hy4 preview vs Step 3.5 Flash

> Hy4 preview is the stronger model overall, scoring 45.3 to 42.3 on the Noometry Index. Step 3.5 Flash costs 8.3× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/hy4-preview-vs-step-3-5-flash
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Hy4 preview scores higher in 3 categories and Step 3.5 Flash in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 55.7 to 42.6.
- The biggest single-benchmark swing is NYT Connections (extended): 68.2% for Hy4 preview and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 256K.

## Snapshot

| | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| Provider | Tencent | StepFun |
| Noometry Index | 45.3 | 42.3 |
| Rank | 73 | 116 |
| Context | 1.05M | 256K |
| Input $/M | $0.83 | $0.10 |
| Output $/M | $2.50 | $0.30 |
| Weights | Open | Open |

## Coding

- Hy4 preview: 51.6 (#38)
- Step 3.5 Flash: 42.4 (#105)

| Benchmark | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 1436 |

## Reasoning

- Hy4 preview: 31.9 (#79)
- Step 3.5 Flash: 22.2 (#202)

| Benchmark | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 68.2% | 28.4% |
| LMArena Hard Prompts | — | 1411 |

## Math

- Hy4 preview: 55.7 (#42)
- Step 3.5 Flash: 42.6 (#84)

| Benchmark | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| ProofBench | 75% | — |
| LMArena Math | — | 1408 |

## Knowledge

- Hy4 preview: —
- Step 3.5 Flash: 39.6 (#132)

| Benchmark | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | — | 1421 |

## Multilingual

- Hy4 preview: —
- Step 3.5 Flash: 50.5 (#119)

| Benchmark | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |

## Instruction Following

- Hy4 preview: —
- Step 3.5 Flash: 73.1 (#124)

| Benchmark | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |

## Long Context

- Hy4 preview: —
- Step 3.5 Flash: 42.8 (#117)

| Benchmark | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | — | 1402 |

## Writing & Preference

- Hy4 preview: —
- Step 3.5 Flash: 58.8 (#113)

| Benchmark | Hy4 preview | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |

## FAQ

### Is Hy4 preview better than Step 3.5 Flash?

Hy4 preview is the stronger model overall, scoring 45.3 to 42.3 on the Noometry Index. Step 3.5 Flash costs 8.3× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

### Which is cheaper, Hy4 preview or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Hy4 preview lists at $0.83 and $2.50.

### Is Hy4 preview or Step 3.5 Flash better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 256K.

### How many benchmarks do Hy4 preview and Step 3.5 Flash share?

1 benchmark has published results for both models. Hy4 preview has 3 scored results on Noometry and Step 3.5 Flash has 19.