Hands-on with Tencent Hunyuan Hy4: Execution enters top-tier open source
HeyAmit_ · x · 2026-08-30
The author tested Tencent Hunyuan's Hy4 preview within WorkBuddyAI. The model features 770B total parameters, 49B active, and 1M+ token context. The standout feature was execution over answers: it breaks down tasks, works across multiple tools, handles long context, writes code, and verifies work. In Tencent's blind test of 203 engineering tasks, Hy4 preview scored 2.99/4, outperforming GLM 5.3 and Kimi K3. It feels more like an agent than a chatbot.
More from coding & agent
- Simon Willison: code mode is the future of tool calling, if it can be sandboxed — springrod · 2026-10-16
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- Gemini CLI fix: substring matching inlined unrequested binary files into model context — priyanshu1976 · 2026-10-16
- Building AI agents on real healthcare claims data: the domain work that makes them work — alex_verem · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Vibe-coded iPhone Duo sniping bot built with Codex in 17 minutes, 41 tests passing — xiaohu · 2026-10-16