Tencent Hunyuan’s Hy3 ranks #25 in Agent Arena and #2 among open models in Frontend Code Arena
arena · x · 2026-07-22
Tencent Hunyuan’s Hy3 lands at #25 overall in Agent Arena
Tencent Hunyuan’s Hy3 is now ranked #25 overall in Agent Arena for open-weight models, with a #5 spot among open-weight models. It also reaches #2 among open models in the Frontend Code Arena, where it places #16 overall.
The post highlights a split profile:
- Strengths: tool use, especially recovery from CLI/bash errors (+2.6%, #25)
- Weakness: steerability, where it struggles to course-correct when users push back (-7.1%, #30)
Agent Arena evaluates models on millions of real-world, long-horizon tasks using web search, filesystem, and terminal tools for workflows like coding, slide decks, web research, app building, and document analysis.
Related event: LMSYS Arena: Hy3 Shines in Frontend Code but Shows Mixed Agent Results(8 posts)→
More from coding & agent
- AgentVille runs local Ollama agents in an open-source pixel town — GeraAI_WW · 2026-07-22
- Claude reportedly beats a black-box AI detector after about seven tries — zacharynado · 2026-07-22
- Antithesis adopts exe to run agents on real machines safely — davidcrawshaw · 2026-07-22
- Every says a $625-a-year membership added $9,000 in MRR in two days — danshipper · 2026-07-22
- ChatGPT Work and Codex now let builders ship and share prototypes with sign-in — gabrielchua · 2026-07-22
- How one developer orchestrates Claude managed agents as specialized “gnomes” — BuyFar3984 · 2026-07-22