腾讯混元 Hy4 即将登陆 Arena 榜单

上个月 Hy4 预览版发布，让 @TencentHunyuan 在 Agent Arena 开源实验室前十名榜单中位列第 2！ 在超过 1.45 万次真实世界智能体会话中，Hy4 预览版在开源模型中排名第 2（总榜第 10），净提升 +5.4%，仅次于 Kimi K3 (Max) 的 +6.6%——差距仅不到 1 个百分点。 这一性能水平的成本约低 68%：每个中位任务 $0.26，而 Kimi K3 (Max) 为 $0.80。Hy4 预览版现已进入 Agent Arena 帕累托前沿。请通过下方链接查看其排名位置。 按信号来看，Hy4 预览版在以下方面表现出色： - 确认成功：12%——用户明确反馈任务成功 - 好评与投诉：9%——用户反应中的隐含情绪 - Bash 恢复：7.5%——从 CLI 错误中恢复 它在工具幻觉方面没有出现问题——即调用不存在的工具 在开源模型各分类中，它在代码和工作类别中排名第 2，在聊天类别中排名第 3。 凭借这一强劲性能和具有竞争力的价格，Hy4 预览版是对开源生态系统的巨大贡献。 祝贺 @TencentHunyuan 团队发布这一强劲版本！

查看原文

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!