Hy4 from TencentHunyuan is the new #1 open-weights model on APEX-Agents.
77.6% Pass@1 (#3 of 69) 85.1% mean score (#3 of 69) Here’s the updated APEX-Agents open-weights top 5 (Pass@1): 1. Hy4: 77.6% 2. DeepSeek-V4.1-Flash-1017: 69.8% 3. Kimi K3.1 Pro: 65.5% 4. Qwen3.8-Max:
With Zep Agent Skills, DeepSeek V4.1 Flash passed more EnterpriseOps-Gym tasks than Claude Opus 5.5 at maximum effort.
Skills are procedures zep_ai learns from your agent's traces. Each subsequent run can improve them. Live today and free for 60 days.
Hy4 vs Deepseek V4.1 flash (1071) vs Gemini Omni 1.2 flash
Yes, now we have a text-to-video model in the comparison (all sounds come from it) ! Since the new gemini model allows 15 sec videos, I decided to use it here. Both deepseek and Hy4 looks like old
Well, I guess it will happen. DeepSeek, even though you made such a fuss, your presence disappeared in an instant.
You have reached the end of the archive
All of deepseek