# Hy4 preview vs Qwen2.5-VL 72B Instruct

> Hy4 preview is the stronger model overall, scoring 44.6 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy4-preview-vs-qwen2-5-vl-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Hy4 preview leads 30.6 to 20.0.
- Hy4 preview is cheaper at $0.83 / $2.50 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Hy4 preview accepts more context: 1.05M tokens versus 131K.

## Snapshot

| | Hy4 preview | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.6 | 29.4 |
| Rank | 73 | 298 |
| Context | 1.05M | 131K |
| Input $/M | $0.83 | $2.80 |
| Output $/M | $2.50 | $8.40 |
| Weights | Open | Open |

## Coding

- Hy4 preview: 51.4 (#36)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | Hy4 preview | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena WebDev | 1633 | — |

## Agentic & Tool Use

- Hy4 preview: —
- Qwen2.5-VL 72B Instruct: 18.4 (#136)

| Benchmark | Hy4 preview | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |

## Reasoning

- Hy4 preview: 30.6 (#75)
- Qwen2.5-VL 72B Instruct: 20.0 (#228)

| Benchmark | Hy4 preview | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| NYT Connections (extended) | 68.2% | — |

## Math

- Hy4 preview: 54.5 (#37)
- Qwen2.5-VL 72B Instruct: —

| Benchmark | Hy4 preview | Qwen2.5-VL 72B Instruct |
|---|---|---|
| ProofBench | 75% | — |

## Multimodal

- Hy4 preview: —
- Qwen2.5-VL 72B Instruct: 32.9 (#92)

| Benchmark | Hy4 preview | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | — | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |

## FAQ

### Is Hy4 preview better than Qwen2.5-VL 72B Instruct?

Hy4 preview is the stronger model overall, scoring 44.6 to 29.4 on the Noometry Index.

### Which is cheaper, Hy4 preview or Qwen2.5-VL 72B Instruct?

Hy4 preview is cheaper. It lists at $0.83 per million input tokens and $2.50 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

### Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 131K.

### How many benchmarks do Hy4 preview and Qwen2.5-VL 72B Instruct share?

0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.