Tencent’s Hy3 ranks No. 5 among open models in Agent Arena
arena · x · 2026-07-22
Tencent’s Hy3 lands at #5 among open-weight models in Agent Arena and is also #2 among open models in Frontend Code Arena.
What the benchmark says
- Overall Agent Arena rank: #25 with -2.2% net improvement.
- Strength: tool use, especially recovering from CLI/bash errors.
- Weakness: steerability — it struggles to course-correct when users push back.
- The benchmark runs on millions of real-world long-horizon agent tasks, including web search, filesystem, terminal, slide decks, app building, and document analysis.
The result positions Hy3 as a strong open model for agentic workflows, but not a leader on overall user satisfaction or steerability.
More from coding & agent
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents — AlishaOutridge · 2026-09-11
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11