# Hy3 vs Step 3.5 Flash

> Hy3 is the stronger model overall, scoring 43.6 to 41.7 on the Noometry Index. Step 3.5 Flash costs 1.5× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/hy3-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Hy3 scores higher in 7 categories and Step 3.5 Flash in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.6 to 41.7.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 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 $0.13 / $0.53 for Hy3.
- Hy3 accepts more context: 262K tokens versus 256K.

## Snapshot

| | Hy3 | Step 3.5 Flash |
|---|---|---|
| Provider | Tencent | StepFun |
| Noometry Index | 43.6 | 41.7 |
| Rank | 79 | 116 |
| Context | 262K | 256K |
| Input $/M | $0.13 | $0.10 |
| Output $/M | $0.53 | $0.30 |
| Weights | Open | Open |

## Coding

- Hy3: 46.6 (#60)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Hy3 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1465 | 1436 |
| LMArena WebDev | 1509 | — |

## Reasoning

- Hy3: 25.0 (#134)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Hy3 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 41.2% | 28.4% |
| LMArena Hard Prompts | 1449 | 1411 |

## Math

- Hy3: 37.4 (#98)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Hy3 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1475 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- Hy3: 40.2 (#108)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Hy3 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1461 | 1422 |

## Multilingual

- Hy3: 53.7 (#60)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Hy3 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1427 | 1386 |
| LMArena Chinese | 1496 | 1448 |
| LMArena French | 1461 | 1421 |
| LMArena Korean | 1390 | 1350 |
| LMArena Russian | 1435 | 1385 |
| LMArena Spanish | 1448 | 1419 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |

## Instruction Following

- Hy3: 75.3 (#68)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Hy3 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1425 | 1385 |

## Long Context

- Hy3: 44.1 (#70)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Hy3 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1443 | 1402 |

## Writing & Preference

- Hy3: 62.5 (#75)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Hy3 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1442 | 1403 |
| LMArena Creative Writing | 1399 | 1357 |
| LMArena Multi-Turn | 1436 | 1405 |

## FAQ

### Is Hy3 better than Step 3.5 Flash?

Hy3 is the stronger model overall, scoring 43.6 to 41.7 on the Noometry Index. Step 3.5 Flash costs 1.5× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.

### Which is cheaper, Hy3 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; Hy3 lists at $0.13 and $0.53.

### Is Hy3 or Step 3.5 Flash better for coding?

Hy3 scores higher on coding benchmarks: 46.6 versus 41.7 in the Noometry coding category.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 256K.

### How many benchmarks do Hy3 and Step 3.5 Flash share?

16 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Step 3.5 Flash has 19.