Tencent Hunyuan Hy4 Tops Open Models on Agent Arena

1 reports archived1 independent sourcesupdated 11/4/2026, 15:15:01

Synthesis & Latest Updates

1 Sources Cross-Validated

Tencent's Hunyuan Hy4 ranks #14 overall on Agent Arena and is projected to lead open-source models upon weight release. It demonstrates superior performance in long-horizon agentic tasks at 62% lower cost than Kimi K3.1 Pro, with significant improvements in success rate and steerability.

LATEST/Tencent's Hunyuan Hy4 ranks #14 overall on Agent Arena and is projected to lead open-source models upon weight release. It demonstrates superior performance in long-horizon agentic tasks at 62% lower cost than Kimi K3.1 Pro, with significant improvements in success rate and steerability.

Hourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first

Arena.ai (@arena)T1Nov 4, 15:15·78 pts
Tencent Hunyuan Hy4 Tops Open Models on Agent Arena
- Hy4 ranks #14 overall on Agent Arena, expected to tie for #1 among open models once weights are released
- Hy4 costs 62% less per task ($0.55) than Kimi K3.1 Pro ($1.46) while scoring within 1 percentage point
- Significant improvements across all key signals: confirmed success, sentiment, steerability, and bash reliability
View Related Reports & Analysis Original Source