Tencent, open weights

# Hy4 preview

> Hy4 preview by Tencent, released August 2026. Ranked #73 of 354 with a Noometry Index of 45.3. API: $0.75 in / $2.25 out per M tokens. 1.05M context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/hy4-preview
- Last updated: 2026-10-10
- Title: Hy4 preview Benchmarks, Price & Rank (October 2026)

Hy4 preview by Tencent ranks 73rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 45.3. Its strongest category is coding, where it ranks 38th. API pricing starts at $0.75 per million input tokens and $2.25 per million output tokens, with a 1.05M-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #73 of 354
- **Index score:** 45.3
- **Evidence:** Reported 3 results
- **Provider:** [![](/logos/tencent.svg) Tencent](https://noometry.com/providers/tencent)
- **Released:** August 28, 2026
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 1.05M
- **Max output:** 64K
- **Input price:** $0.75 / M
- **Output price:** $2.25 / M
- **Blended price:** $1.13 / M
- **Output speed:** Not measured
- **Value:** #118 of 219
- **Knowledge cutoff:** Unknown
- **Input:** text
- **Hugging Face:** [tencent/Hy4-preview](https://huggingface.co/tencent/Hy4-preview)

## Category scores

Each category score combines every public result we have in that category.

Hy4 preview category scores

1.  Coding 51.6
2.  Reasoning 31.9
3.  Math 55.7
4.  2030405060

Hy4 preview category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 51.6 | #38 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 31.9 | #79 | 1 |
| [Math](https://noometry.com/best/math) | 55.7 | #42 | 1 |

## Strengths and weaknesses

Categories where Hy4 preview places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Hy4 preview: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 51.6 | +12.9 | #38 of 340, top 12% |

### Weakest categories

Hy4 preview: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 31.9 | +8.3 | #79 of 350, top 23% |

## Closest competitors

The models ranked just above and below Hy4 preview. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Hy4 preview
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [GPT-5.3 Codex](https://noometry.com/models/gpt-5-3-codex) | #69 | 45.8 | $4.81 | — | [Compare](https://noometry.com/compare/gpt-5-3-codex-vs-hy4-preview) |
| [Kimi K2 Thinking Turbo](https://noometry.com/models/kimi-k2-thinking-turbo) | #70 | 45.8 | — | — | [Compare](https://noometry.com/compare/hy4-preview-vs-kimi-k2-thinking-turbo) |
| [Qwen3.5 Max Preview](https://noometry.com/models/qwen3-5-max-preview) | #71 | 45.3 | — | — | [Compare](https://noometry.com/compare/hy4-preview-vs-qwen3-5-max-preview) |
| [Qwen3.7 Plus](https://noometry.com/models/qwen3-7-plus) | #72 | 45.3 | $0.70 | — | [Compare](https://noometry.com/compare/hy4-preview-vs-qwen3-7-plus) |
| [MiMo-V2.5-Pro](https://noometry.com/models/mimo-v2-5-pro) | #74 | 45.2 | $0.54 | — | [Compare](https://noometry.com/compare/hy4-preview-vs-mimo-v2-5-pro) |
| [Gemini 2.5 Pro](https://noometry.com/models/gemini-2-5-pro) | #75 | 45.0 | $3.44 | 5 | [Compare](https://noometry.com/compare/gemini-2-5-pro-vs-hy4-preview) |
| [GPT-5.4 mini](https://noometry.com/models/gpt-5-4-mini) | #76 | 45.0 | $1.69 | 10 | [Compare](https://noometry.com/compare/gpt-5-4-mini-vs-hy4-preview) |
| [Amazon Nova Experimental Chat 26 02 10](https://noometry.com/models/amazon-nova-experimental-chat-26-02-10) | #77 | 44.5 | — | — | [Compare](https://noometry.com/compare/amazon-nova-experimental-chat-26-02-10-vs-hy4-preview) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Hy4 preview Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1632 | #14 of 113, top 13% |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |

### Reasoning

Hy4 preview Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 68.2% | #52 of 91, top 58% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |

### Math

Hy4 preview Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ProofBench](https://noometry.com/benchmarks/proofbench) | 75% | #13 of 77, top 17% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## API pricing by provider

Hy4 preview API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [deepinfra](https://deepinfra.com/models) | $0.83 | $2.50 | $0.042 | 2026-10-10 |
| [openrouter](https://openrouter.ai/tencent/hy4-preview) | $0.75 | $2.25 | $0.0378 | 2026-10-10 |

[All Tencent API prices →](https://noometry.com/llm-pricing/tencent) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare Hy4 preview

-   [Hy4 preview vs Qwen3.7 Plus](https://noometry.com/compare/hy4-preview-vs-qwen3-7-plus)
-   [Hy4 preview vs MiMo-V2.5-Pro](https://noometry.com/compare/hy4-preview-vs-mimo-v2-5-pro)
-   [Hy4 preview vs Qwen3.5 Max Preview](https://noometry.com/compare/hy4-preview-vs-qwen3-5-max-preview)
-   [Hy4 preview vs Gemini 2.5 Pro](https://noometry.com/compare/gemini-2-5-pro-vs-hy4-preview)
-   [Hy4 preview vs Kimi K2 Thinking Turbo](https://noometry.com/compare/hy4-preview-vs-kimi-k2-thinking-turbo)
-   [Hy4 preview vs GPT-5.4 mini](https://noometry.com/compare/gpt-5-4-mini-vs-hy4-preview)
-   [Hy4 preview vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-hy4-preview)
-   [Hy4 preview vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-hy4-preview)
-   [Hy4 preview vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-hy4-preview)
-   [Hy4 preview vs Kimi K3](https://noometry.com/compare/hy4-preview-vs-kimi-k3)
-   [Hy4 preview vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-hy4-preview)
-   [Hy4 preview vs Qwen3.8 Max](https://noometry.com/compare/hy4-preview-vs-qwen3-8-max)
-   [Hy4 preview vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-hy4-preview)
-   [Hy4 preview vs Muse Spark 1.3](https://noometry.com/compare/hy4-preview-vs-muse-spark-1-3)

## Other Tencent models

-   [Hy3](https://noometry.com/models/hy3)44.2
-   [Hunyuan Vision 1.5](https://noometry.com/models/hunyuan-vision-1-5)43.1
-   [Hunyuan T1 20250711](https://noometry.com/models/hunyuan-t1)42.5
-   [Hunyuan Turbos 20250226](https://noometry.com/models/hunyuan-turbos)41.3
-   [Hunyuan Turbo 0110](https://noometry.com/models/hunyuan-turbo)39.6
-   [Hunyuan Large 2025 02 10](https://noometry.com/models/hunyuan-large)38.6
-   [Hunyuan Standard 2025 02 10](https://noometry.com/models/hunyuan-standard)37.9
-   [Hunyuan Large Vision](https://noometry.com/models/hunyuan-large-vision)37.6

## Frequently asked questions

### How good is Hy4 preview?

Hy4 preview by Tencent ranks 73rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 45.3. Its strongest category is coding, where it ranks 38th. API pricing starts at $0.75 per million input tokens and $2.25 per million output tokens, with a 1.05M-token context window.

### How much does Hy4 preview cost?

Hy4 preview costs $0.75 per million input tokens and $2.25 per million output tokens on openrouter, with cached input at $0.0378.

### What is Hy4 preview's context window?

Hy4 preview accepts up to 1.05M tokens of input and can write up to 64K tokens in one response.

### Is Hy4 preview open source?

Yes. Hy4 preview's weights are downloadable from Hugging Face (tencent/Hy4-preview); check the license for commercial terms.

### What are Hy4 preview's strengths and weaknesses?

Relative to other ranked models, Hy4 preview places best in coding and lowest in reasoning.

### What is Hy4 preview best at?

Its best category is coding, where it ranks 38th on Noometry.

### Cite this page

Noometry. (2026). Hy4 preview benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/hy4-preview

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/hy4-preview.md).