Tencent Hunyuan Hy4 preview ranks #2 among open models in Agent Arena
The notable detail is cost efficiency: Hy4 preview nearly matches Kimi K3 (Max) on agent performance while cutting per-task spend by about two-thirds, placing it on the Agent Arena Pareto frontier. Teams running open-source agent stacks on a budget should benchmark it against Kimi K3 (Max) when the full Hy4 release lands. Its signal-level strengths in Bash Recovery and tool reliability matter for CLI-heavy workflows.
Tencent (Hunyuan) is preparing the full release of Hy4 following a preview launch last month. In Agent Arena, the Hy4 preview ranked #2 among open models (#10 overall) across more than 14.5K real-world agent sessions, with a +5.4% net improvement, just behind Kimi K3 (Max) at +6.6%. It achieved this at roughly 68% lower cost: US$0.26 per median task versus US$0.80 for Kimi K3 (Max). By signal, it scored 12% on Confirmed Success, 9% on Praise vs. Complaint and 7.5% on Bash Recovery, and showed no Tool Hallucination issues. It is also #2 among open models in Code and Work and #3 in Chat.
Hy4 from @TencentHunyuan is coming soon. Stay tuned to see where this new release lands in the arena. Arena.ai @arena Last month’s Hy4 preview launch landed @TencentHunyuan the #2 spot on the top 10 labs in Agent Arena among open-source labs! Across 14.5K+ real-world agent sessions, Hy4 preview ranks #2 among open models ( #10 overall) with a +5.4% net improvement, trailing only Kimi K3 (Max) at +6.6%—a gap of just nearly 1 percentage point. This level of performance comes at roughly 68% lower cost: $0.26 per median task, compared with $0.80 for Kimi K3 (Max). Hy4 preview is now on the Agent Arena Pareto frontier. See the link below to explore its placement. By signal, Hy4 preview excels in: - Confirmed Success: 12% — explicit user feedback that the task worked - Praise vs. Complaint: 9% — implicit sentiment in user reactions - Bash Recovery: 7.5% — recovery from CLI errors It shows no issues with Tool Hallucination — calling tools that don’t exist By category among open models, it’s also #2 in Code and Work, and #3 in Chat. With this strong performance at a competitive price, Hy4 preview is a huge contribution to the open-source ecosystem. Congrats to the @TencentHunyuan team on this strong release! 🔗 View Quoted Tweet 💬 6 🔄 2 ❤️ 38 👀 4636 📊 7 ⚡
- AWS Machine Learning Blog16:32原文
