LMArena Benchmarks: Open-Weight Hy3 Ranks #2 in Frontend Code Arena
arena · x · 2026-07-22
LMArena released the latest benchmark results for the Frontend Code and Agent Arenas. The open-weight model Hy3 performed impressively, ranking #2 among open-weight models (#16 overall) in the Frontend Code Arena, and made the top 20 in reference-based design, gaming, and content creation tools.
However, in the Agent Arena based on over 8,000 live agentic sessions, Hy3 ranked #25 overall with a -2.2% net improvement. It showed declines in confirmed success and steerability, though slight improvements were noted in Bash recovery and tool hallucination control.
More from coding & agent
- 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
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Agile co-author Ron Jeffries publishes 'Resist AI', urging developers to push back — mborch · 2026-09-11