Tencent, open weights

# Hy3

> Hy3 by Tencent, released July 2026. Ranked #79 of 354 with a Noometry Index of 44.2. API: $0.0825 in / $0.33 out per M tokens. 262K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/hy3
- Last updated: 2026-10-10
- Title: Hy3 Benchmarks, Price & Rank (October 2026) | Noometry

Hy3 by Tencent ranks 79th of 354 ranked models on the Noometry Index as of October 2026, with a score of 44.2. Its strongest category is coding, where it ranks 63rd. API pricing starts at $0.0825 per million input tokens and $0.33 per million output tokens, with a 262K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #79 of 354
- **Index score:** 44.2
- **Evidence:** Confirmed 19 results
- **Provider:** [![](/logos/tencent.svg) Tencent](https://noometry.com/providers/tencent)
- **Released:** July 6, 2026
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 262K
- **Max output:** 128K
- **Input price:** $0.0825 / M
- **Output price:** $0.33 / M
- **Blended price:** $0.14 / M
- **Output speed:** Not measured
- **Value:** #18 of 219
- **Knowledge cutoff:** Unknown
- **Input:** text
- **Hugging Face:** [tencent/Hy3](https://huggingface.co/tencent/Hy3)

## Category scores

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

Hy3 category scores

1.  Coding 46.8
2.  Reasoning 26.1
3.  Math 40.1
4.  Knowledge 40.8
5.  Multilingual 53.5
6.  Instruction Following 75.1
7.  Long Context 44.1
8.  Writing & Preference 62.2
9.  020406080

Hy3 category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 46.8 | #63 | 2 |
| [Reasoning](https://noometry.com/best/reasoning) | 26.1 | #136 | 2 |
| [Math](https://noometry.com/best/math) | 40.1 | #93 | 1 |
| [Knowledge](https://noometry.com/best/knowledge) | 40.8 | #114 | 1 |
| [Multilingual](https://noometry.com/best/multilingual) | 53.5 | #65 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 75.1 | #70 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 44.1 | #75 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 62.2 | #81 | 3 |

## Strengths and weaknesses

Categories where Hy3 places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Hy3: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 46.8 | +8.1 | #63 of 340, top 19% |
| [Multilingual](https://noometry.com/best/multilingual) | 53.5 | +6.1 | #65 of 297, top 22% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 75.1 | +3.8 | #70 of 305, top 23% |

### Weakest categories

Hy3: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 26.1 | +2.5 | #136 of 350, top 39% |
| [Knowledge](https://noometry.com/best/knowledge) | 40.8 | +3.5 | #114 of 314, top 37% |
| [Math](https://noometry.com/best/math) | 40.1 | +3.6 | #93 of 327, top 29% |

## Closest competitors

The models ranked just above and below Hy3. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Hy3
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [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-hy3) |
| [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-hy3) |
| [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-hy3) |
| [DeepSeek-V3.2-Exp](https://noometry.com/models/deepseek-v3-2-exp) | #78 | 44.3 | $0.29 | 16 | [Compare](https://noometry.com/compare/deepseek-v3-2-exp-vs-hy3) |
| [Inkling](https://noometry.com/models/inkling) | #80 | 44.1 | $2.57 | — | [Compare](https://noometry.com/compare/hy3-vs-inkling) |
| [Claude Sonnet 4.5](https://noometry.com/models/claude-sonnet-4-5) | #81 | 44.1 | $6 | 85 | [Compare](https://noometry.com/compare/claude-sonnet-4-5-vs-hy3) |
| [Chatgpt 4o Latest 20250326](https://noometry.com/models/chatgpt-4o) | #82 | 43.8 | — | 21 | [Compare](https://noometry.com/compare/chatgpt-4o-vs-hy3) |
| [ERNIE 5.1](https://noometry.com/models/ernie-5-1) | #83 | 43.8 | — | — | [Compare](https://noometry.com/compare/ernie-5-1-vs-hy3) |

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

Hy3 Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1508 | #46 of 113, top 41% |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1355 |  |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1464 | #68 of 294, top 24% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1422 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Reasoning

Hy3 Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 17.2% |  |  | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 41.2% | #66 of 91, top 73% | high | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1447 | #69 of 297, top 24% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1413 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Math

Hy3 Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1424 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1475 | #33 of 285, top 12% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

Hy3 Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1460 | #62 of 273, top 23% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1423 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

Hy3 Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1426 | #65 of 297, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1390 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1433 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1493 | #53 of 285, top 19% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1424 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1461 | #48 of 223, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1439 | #58 of 231, top 26% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1392 | #67 of 211, top 32% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1395 | #61 of 213, top 29% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1432 | #64 of 283, top 23% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1398 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1456 | #42 of 226, top 19% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1399 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Hy3 Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1426 | #65 of 298, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1383 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Hy3 Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1402 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1442 | #62 of 291, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Hy3 Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1401 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1439 | #64 of 297, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1339 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1402 | #75 of 295, top 26% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1436 | #77 of 295, top 27% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1411 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

Hy3 API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [deepinfra](https://deepinfra.com/models) | $0.13 | $0.53 | $0.033 | 2026-10-10 |
| [openrouter](https://openrouter.ai/tencent/hy3) | $0.0825 | $0.33 | $0.0206 | 2026-10-10 |

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

## Compare Hy3

-   [Hy3 vs DeepSeek-V3.2-Exp](https://noometry.com/compare/deepseek-v3-2-exp-vs-hy3)
-   [Hy3 vs Inkling](https://noometry.com/compare/hy3-vs-inkling)
-   [Hy3 vs Amazon Nova Experimental Chat 26 02 10](https://noometry.com/compare/amazon-nova-experimental-chat-26-02-10-vs-hy3)
-   [Hy3 vs Claude Sonnet 4.5](https://noometry.com/compare/claude-sonnet-4-5-vs-hy3)
-   [Hy3 vs GPT-5.4 mini](https://noometry.com/compare/gpt-5-4-mini-vs-hy3)
-   [Hy3 vs Chatgpt 4o Latest 20250326](https://noometry.com/compare/chatgpt-4o-vs-hy3)
-   [Hy3 vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-hy3)
-   [Hy3 vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-hy3)
-   [Hy3 vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-hy3)
-   [Hy3 vs Kimi K3](https://noometry.com/compare/hy3-vs-kimi-k3)
-   [Hy3 vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-hy3)
-   [Hy3 vs Qwen3.8 Max](https://noometry.com/compare/hy3-vs-qwen3-8-max)
-   [Hy3 vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-hy3)
-   [Hy3 vs Muse Spark 1.3](https://noometry.com/compare/hy3-vs-muse-spark-1-3)

## Other Tencent models

-   [Hy4 preview](https://noometry.com/models/hy4-preview)45.3
-   [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 Hy3?

Hy3 by Tencent ranks 79th of 354 ranked models on the Noometry Index as of October 2026, with a score of 44.2. Its strongest category is coding, where it ranks 63rd. API pricing starts at $0.0825 per million input tokens and $0.33 per million output tokens, with a 262K-token context window.

### How much does Hy3 cost?

Hy3 costs $0.0825 per million input tokens and $0.33 per million output tokens on openrouter, with cached input at $0.0206.

### What is Hy3's context window?

Hy3 accepts up to 262K tokens of input and can write up to 128K tokens in one response.

### Is Hy3 open source?

Yes. Hy3's weights are downloadable from Hugging Face (tencent/Hy3); check the license for commercial terms.

### What are Hy3's strengths and weaknesses?

Relative to other ranked models, Hy3 places best in coding, multilingual, instruction following and lowest in reasoning, knowledge, math.

### What is Hy3 best at?

Its best category is coding, where it ranks 63rd on Noometry.

### Cite this page

Noometry. (2026). Hy3 benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/hy3

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/hy3.md).