Tencent Hunyuan Hy4 preview hits #5 in WebDev Arena, #3 among open models
TencentHunyuan · x · 2026-08-28
Arena announced that Tencent Hunyuan Hy4 preview scored 1633 points (AutoEval) in the Code Arena: WebDev leaderboard, ranking around #5 overall—a big jump from Hy3's #31 (+115 points). Among open models it sits at roughly #3 versus Hy3's #7. Note this is an early AutoEval score, where a reward model trained on Arena human-preference data votes automatically in place of live votes; scores may shift as more human votes arrive. The Hunyuan team reposted with encouragement.
More from Models
- Users suspect DeepSeek V4 quality drop due to routing changes — l33thax0r_ · 2026-08-28
- PhoneLLM Alpha 1 Trends on Hugging Face: Voice Agent Model with MoE — pipecat-ai · 2026-08-28
- Why do research labs prefer Off-Policy Distillation for model improvement? — miifanboy · 2026-08-28
- 4x3090 Benchmarks: 27B Q8KXL at 32GB Beats Next IQ3 at 82GB on Both Speed and Security Tasks — Repulsive_Initial308 · 2026-08-28
- For Agent Memory, the Boring DeepSeek Non-Thinking Pass Wins on Speed and Accuracy — Brave_Pressure_9886 · 2026-08-28
- HALP: AI can know it's about to hallucinate before generating a single token — thisdudelikesAI · 2026-08-28