Hy4 preview
Tencent · Open Weight · rank 55 · bench-align-v5
Self-hostedCanonical idhy4-preview
Access typeOpen Weight
Blended $/1M$1.2575% input / 25% output
Capability shape
Seven axes from the ranking source. A missing axis is drawn as a gap.
Runtime service evidence
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedUnavailable
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | 41 tok/s | 2026-09-17 | 2026-09-17 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Endpoint and price matrix
Every published price component, including cache reads and writes.
| Component | USD | Evidence |
|---|---|---|
| Input / 1M tokens | $0.83 | |
| Output / 1M tokens | $2.50 | |
| Cache read / 1M tokens | $0.042 | |
| Cache write / 1M tokens | Unavailable | |
| Blended / 1M (75% input / 25% output) | $1.25 |
Self-hosted listingTencent publishes Hy4 preview under Apache 2.0 for self-hosting and does not publish a first-party hosted token rate for this exact checkpoint. We represent the open-weight row as self-host/free-per-token before infrastructure costs; the separate FP8 checkpoint is a quantization of the same model rather than a separately priced API SKU.The rates above are a hosted price matched from another provider, not a first-party list price.
Workload-aware monthly cost example
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Benchmark record
27 matched benchmark rows with their published value, unit, and provenance.
Knowledge
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 92.3 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| GPQA-D GPQA Diamond | 92.3 | Graduate-level science questions | Graduate level | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
| HLE Humanity's Last Exam | 55.4 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| HLE w/o tools Humanity's Last Exam without tools | 43.4 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
Coding
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 (provider run) | 85.4 | Terminal-based software-agent tasks | Professional software engineering | DeepSeek V4 Flash 0731 update |
| SWE-bench Pro SWE-bench Pro | 65.7 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| SWE Multilingual SWE Multilingual | 82.9 | Multilingual software-engineering tasks | Professional software engineering | MiniMax M2.7: Early Echoes of Self-Evolution |
| ProgramBench ProgramBench: Can Language Models Rebuild Programs From Scratch? | 17.5 | 200 program reconstruction tasks | Full-repository software architecture | ProgramBench: Can Language Models Rebuild Programs From Scratch? |
| PostTrain Bench PostTrain Bench | 35.6 | Post-training software-engineering tasks | Frontier software engineering | Kimi K3: Open Frontier Intelligence |
| NL2Repo NL2Repo | 58.9 | Natural language to repository tasks | System-level software comprehension | MiniMax M2.7: Early Echoes of Self-Evolution |
| DeepSWE DeepSWE | 64.3 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
Mathematics
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| Apex Apex | 74.2 | Advanced mathematical reasoning | Frontier math reasoning | DeepSeek-V4 Technical Report |
Reasoning
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| CritPt Critical Physics Tasks | 16.9 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
Agentic
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| DRACO Data Research and Analysis with Complex Operations | 77.2 | Agentic data research and analysis tasks | Professional data analysis | Claude Opus 5 System Card |
| Terminal-Bench 2.1 Terminal-Bench 2.1 (provider run) | 85.4 | Terminal-based software-agent tasks | Professional software engineering | DeepSeek V4 Flash 0731 update |
| HLE w/ tools Humanity's Last Exam with tools | 55.4 | Expert questions with tool use | Frontier tool-augmented reasoning | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA | 1678 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| CyberGym CyberGym | 78.4 | 1,507 vulnerability analysis instances | Real-world cybersecurity | CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale |
| JobBench JobBench | 61.7 | 130 tasks across 35 occupations | Professional multi-source workflows | JobBench: Aligning Agent Work With Human Will |
| MCP Atlas MCP Atlas | 83.7 | Tool-integrated agent tasks | Advanced tool use | Introducing GPT-5.4 mini and nano |
| Toolathlon-Verified Toolathlon-Verified | 74.1 | Verified multi-tool workflows | Advanced tool use | Kimi K3: Open Frontier Intelligence |
| AutomationBench AutomationBench | 32.1 | 600 public automation tasks | Long-horizon automation | Kimi K3: Open Frontier Intelligence |
| Agents' Last Exam Agents' Last Exam | 22.8 | Agent tasks | Advanced agentic work | DeepSeek V4 Flash 0731 update |
| APEX-Agents APEX-Agents | 37.1 | Professional-services agent tasks | Long-horizon professional work | Kimi K3: Open Frontier Intelligence |
| WideResearch WideResearch | 83.9 | Open-ended research tasks | Broad research-agent workflows | Qwen3.6 launch benchmarks |
| BankerToolBench BankerToolBench | 78.6 | Finance and banking tool-use tasks | Professional finance-agent workflows | MiniMax M3 model card |
Multimodal & Grounded
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| OfficeQA Pro OfficeQA Pro | 66.2 | Document and spreadsheet tasks | Enterprise grounded reasoning | OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning |
Lifecycle and limitations log
Lifecycle events the source associates with this model, plus what this profile does not claim.
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 claimValues 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 — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-17 17:17 UTC.