Tencent’s Hy3 ranks 25th in Agent Arena after 8,000+ live agent sessions
arena · x · 2026-07-22
Tencent’s Hy3 lands at #25 in Agent Arena with a mixed scorecard
Agent Arena’s latest leaderboard puts Hy3 at #25 overall after more than 8,000 live agentic sessions.
- Overall rank: 25
- Confirmed Success: 27th, with -4.6% net improvement
- Praise vs Complaint: 20th, -2.9%
- Steerability: 30th, -7.1%
- Bash Recovery: 25th, +2.6%
- Tool Hallucination: 25th, +0.9%
The post is essentially a snapshot of where Hy3 stands on real agent tasks: mediocre overall, weaker on success and steerability, but somewhat better at recovering from shell errors.
More from coding & agent
- Dev turns DJI Mavic into local AI security drone built with Opus 5.5 — alexcovo_eth · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27
- AI agents may soon become the only way to run code, not just write it — IgorCarron · 2026-10-27