Hy4 is already outperforming GPT-6.1 Sol and Claude Opus 5.5 on multiple benchmarks.
This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
Hy4 is already outperforming GPT-6.1 Sol and Claude Opus 5.5 on multiple benchmarks. It’s now live on Tencent Cloud and OpenRouter! The model weights aren't available just yet, but stay tuned. Here are the detailed benchmark results👇
Posted by 智东西China AI News (3k followers) 1 h ago · 12 likes · 504 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Meet Hy4. — @TencentAI_News
- Tried Tencent Hy (Hy4) on a chart from my SGLang Omni notes: 9 series on a log2 x-axis,… — @GenAI_is_real
- Meet Mark-Engineer-V3-1.5B: a 1.5B parameter text-generation model built for systems… — @HuggingModels
- 字幕都写好了，画面却卡住？如今一份 SRT 就能直接变成白板手绘视频。 — @bkdgiffug
- This might be the most fun Hermes plugin yet. — @HermesWatcher
- DeepSeek-v4.1-Flash-1017 can do pretty much any style you ask it to. In fact that is one… — @ItsmeAjayKV
- Everyone will soon have their own agent. The hard part is getting them to work together. — @Ronny_MiniMax
- 💥炸裂！腾讯混元Hy-4正式版性能直逼顶级模型，价格直接打穿底！ — @NFT_Chen
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.4k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 07:07 UTC. Full method.