Hy4-preview
Tencent·
LLMsopen-weightcloud + localFrontier
Overview
Preview of Tencent's next-generation Hunyuan flagship: a 770B-parameter MoE activating 49B per token, with a 1M-token context window. Open-weight under Apache 2.0 with an FP8 checkpoint alongside BF16, tuned for coding agents, complex tool-use workflows and productivity tasks, and trained on domain data from Tencent's software, gaming and finance teams.
Capabilities and innovations
770B total / 49B active MoE1M token context windowCoding-agent and tool-use focusApache 2.0 licenseTencent-internal software, gaming and finance domain dataFP8 checkpoint shipped alongside BF16
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 92.3% | vendor GPQA Diamond 92.3, vendor model card. |
| SWE-bench Pro | 65.7% | vendor SWE-bench Pro 65.7, vendor model card. |
- Humanity’s Last Exam (no tools): independent evaluation pending — Fresh release (2026-08-28); no independent no-tools measurement published yet.
- MMLU-Pro: independent evaluation pending — Fresh release; vals.ai / Artificial Analysis runs pending.
- Terminal-Bench 2.x: independent evaluation pending — Fresh release; no Terminal-Bench 2.x measurement published yet.
- MMMU-Pro: not reported by the vendor — Text-only preview.
API pricing
$0.834 per million input tokens, $2.501 per million output tokens (USD, cheapest OpenRouter endpoint, checked 2026-08-31)
Architecture and hardware
- Parameters
- 770B total, 49B active per token (MoE)
- Estimated VRAM at Q4
- ~443 GB, Frontier class
Links
More from Tencent
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.