Tencent Hunyuan Hy4 ranks 14th overall on Agent Arena, with a per-task cost about 62% lower than Kimi K3.1 Pro
Agent Arena shows that Tencent Hunyuan Hy4 ranks 14th overall on 8.5K+ real long-horizon agent sessions, with a net improvement of +4.7%, and has entered the Agent Arena Pareto frontier. Its per-task cost is $0.55, about 62% lower than the $1.46 of Kimi K3.1 Pro (Max), and the score gap between the two is within 1 percentage point. Compared with Hy4 preview's 25th place (+1.1%), this is an improvement of 3.6 percentage points; all four signals—confirmed success, positive-to-complaint ratio, steerability, and Bash reliability—improved. Hy4 is currently closed-source; once its weights are released, it will tie with Kimi K3.1 Pro for 1st among open-source models.
View original post👋Hy4 is here, new with vision. Firmly among the leading open models. More productive everywhere: finance, frontend, game, officework, research… Built responsibly, with cyber/biosecurity in mind. Try it out and let us know! 🔗：https://t.co/ZzL4DtgH3h https://t.co/xceRxN6ueT
View original
👋Hy4 is here, new with vision. Firmly among the leading open models. More productive everywhere: finance, frontend, game, officework, research… Built responsibly, with cyber/biosecurity in mind. Try it out and let us know! 🔗：https://t.co/ZzL4DtgH3h https://t.co/xceRxN6ueT
Body
Exciting news from Agent Arena: Hy4 by @TencentHunyuan just landed #14 overall. Currently proprietary, but once its weights are released it will tie with Kimi K3.1 Pro for #1 among open models!
Across +8.5K real-world, long-horizon agentic sessions from our global community of users, Hy4 delivers +4.7% net improvement and joins the Agent Arena Pareto frontier. At $0.55/task, Hy4 costs about 62% less than Kimi K3.1 Pro (Max) at $1.46/task, and the two models’ scores are within 1 percentage point.
This release is a +3.6 percentage pt improvement from Hy4 preview at #25 with +1.1%. In fact, Hy4 improved across all key signals: - Confirmed Success (explicit “yes, that worked” from users): #11 with +8.7% (up from #16 with +4.9%) - Praise vs Complaint (sentiment in user reactions): #18 with +3.8% (up from #24 with +1%) - Steerability (responding to user corrections): #14 with +5.7% (up from #27 with +0.21%) - Bash Reliability (successful shell commands): #20 with +6.2% (up from #41 with -3.1%)
Congrats to the @TencentHunyuan team on this release!