# Hy4

Tencent · Pending · rank 25 · bench-align-v5

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/models/hy4  
JSON: https://modelchoice.dev/api/model/hy4

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `hy4` | — |
| Overall score | 68.5 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 77 | Observed 2026-11-21 · source benchlm:models |
| Context window | 1M tokens | Observed 2026-11-21 · source benchlm:models |
| Modalities (models.dev) | Input: text, image · Output: text | Observed 2026-11-21 · source openrouter:pricing |
| Release date | 2026-11-04 | Observed 2026-11-21 · source benchlm:models |
| Access type | Pending | — |
| Blended $/1M (75% input / 25% output) | $1.25 | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero. Beside each score is BenchLM's separate verified score for that axis; the two are published side by side and are not interchangeable.

| Axis | Score | Evidence | Verified (BenchLM) | Verified evidence |
| --- | --- | --- | --- | --- |
| Agentic | Unavailable | Unavailable · source benchlm:models | 81.1 | Observed 2026-11-21 · source benchlm:models |
| Coding | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Knowledge | Unavailable | Unavailable · source benchlm:models | 82.9 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models | 77.8 | Observed 2026-11-21 · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Math | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |
| Throughput | 89 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source openrouter:endpoints |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $0.83 | Observed 2026-11-21 · source benchlm:pricing |
| Output / 1M tokens | $2.50 | Observed 2026-11-21 · source benchlm:pricing |
| Cache read / 1M tokens | $0.042 | Observed 2026-11-21 · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $1.25 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Unavailable · source livebench:table |

**Pricing note.** Tencent Cloud TokenHub lists Hy4 at $0.834 input, $0.042 cached input, and $2.501 output per million tokens, the same list price as Hy4 preview, which Tencent's launch post confirms. Until December 31, 2026 (Beijing time), TokenHub bills Hy4 at 50% of list price, and OpenRouter's tencent/hy4 listing shows the same half rate ($0.417 input, $0.021 cached input, $1.2505 output). We store the list price. Tencent plans to open-source the weights, so source type stays pending until a checkpoint is public.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | $3.52 |
| Modelled tokens | 2.82M |

## Benchmark record

23 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| HLE (Humanity's Last Exam) | 59.1 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ProgramBench (ProgramBench: Can Language Models Rebuild Programs From Scratch?) | 30.0 | 200 program reconstruction tasks | Full-repository software architecture | [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://programbench.com/static/paper.pdf) |
| DeepSWE | 74.9 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |
| FrontierCode 2.0 | 31.0 | 132 private software-engineering tasks | Frontier coding-agent quality | [FrontierCode 2.0](https://cognition.com/blog/frontier-code-2.0) |
| PostTrainBench (PostTrainBench v1.2) | 35.2 | Post-training four base models on six benchmarks | Autonomous ML engineering | [PostTrainBench](https://posttrainbench.com/) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 4.0 | 44.40 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.0](https://www.tbench.ai/news/terminal-bench-4-0) |
| Terminal-Bench-Science 0.1 | 19.8 | 70 expert-curated scientific research workflows | Frontier scientific research workflows | [Terminal-Bench-Science 0.1](https://www.terminal-bench-science.ai/) |
| HLE w/ tools (Humanity's Last Exam with tools) | 59.1 | Expert questions with tool use | Frontier tool-augmented reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| AutomationBench | 56.2 | 600 public automation tasks | Long-horizon automation | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| Agents' Last Exam | 41.0 | Agent tasks | Advanced agentic work | [DeepSeek V4 Flash 0731 update](https://api-docs.deepseek.com/zh-cn/updates/) |
| APEX-Agents | 75.2 | Professional-services agent tasks | Long-horizon professional work | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| CWE-bench (CWE-bench v2) | 64.1 | Audit and patch C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories; 100 public and 150 held-out tasks | Frontier agent evaluation | [CWE-bench v2 leaderboard and methodology](https://cwe-bench.com/) |
| Terminal-Bench 4.1 | 37.90 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.1](https://www.tbench.ai/news/terminal-bench-4-1) |
| OSWorld 2.1 (OSWorld 2.1 (all 108 tasks)) | 78.9 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | [OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1)](https://github.com/xlang-ai/OSWorld-V2/releases) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| MMMU-Pro (Massive Multi-discipline Multimodal Understanding Pro) | 78.6 | Multimodal academic reasoning | Frontier multimodal | [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://arxiv.org/abs/2409.02813) |
| Design Arena Website (Design Arena Website Elo) | 1247 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |
| ZeroBench w/ Python (ZeroBench_main with Python) | 55.4 | Visual reasoning questions with Python | Tool-augmented visual reasoning | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| ParseBench-1 (ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release)) | 73.72 | 2,078 human-verified enterprise pages from insurance, finance and government documents | No method is strong on all five dimensions; charts and visual grounding separate the field | [ParseBench: A Document Parsing Benchmark for AI Agents](https://arxiv.org/abs/2604.08538) |
| ExtractBench (LlamaIndex) (ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard)) | 80.66 | 370 documents, 4,869 pages, 8 business domains, 67 document types, each with a JSON Schema | Short documents are near solved; long record lists and grounding separate systems | [ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction](https://arxiv.org/abs/2607.29677) |
| ExtractBench Pro (ExtractBench Pro: long-tail document extraction challenges (LlamaIndex)) | 23 | 100 synthetic documents, 2,622 pages, 86 document types, six challenge groups | The best system completes 58 of 100 documents perfectly; several complete none | [ExtractBench Pro leaderboard and challenge descriptions](https://www.extractbench.ai/pro) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Cookie-Bench (Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation) | 88.8 | 1,000 web development queries (React setting) | Interactive web apps and static pages across three tiers | [Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation](https://arxiv.org/abs/2605.30000) |
| BlenderWorld (text-only) (BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References (text-only subset)) | 76.8 | 78 text-brief 3D creation tasks in Blender | Long-horizon 3D modeling and scene building | [BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References](https://arxiv.org/abs/2610.23986) |
| NYT Connections (NYT Connections LLM Benchmark (extended version)) | 83.5 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | [NYT Connections LLM Benchmark (Lech Mazur, GitHub)](https://github.com/lechmazur/nyt-connections) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

No lifecycle event references this model. That is not evidence the model has no lifecycle plan — only that this source published none.

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-11-21 04:17 UTC.
