Tencent Hunyuan Hy4 Ranks First on the APEX-Agents Open-Weights Model Leaderboard
The APEX-Agents leaderboard published by Mercor shows that Tencent Hunyuan Hy4, with 77.6% Pass@1, is the top-ranked open-weights model, placing 3rd among 69 models with a mean score of 85.1%. The top five open-weights models are, in order, Hy4 77.6%, DeepSeek-V4.1-Flash-1017 69.8%, Kimi K3.1 Pro 65.5%, Qwen3.8-Max 63.3%, and MiMo V2.6 Flash RL 57.4%. Hy4 is also the top open-weights model in the three subcategories of management consulting, investment banking analysis, and corporate law, with scores of 85.6%, 75.3%, and 71.9%, respectively.
Why read this
AI score 60
The leaderboard provides a score comparison of Hy4 against open-source models such as DeepSeek, Kimi, and Qwen on APEX-Agents, which can be used to assess where open-source models stand on agentic tasks.
Topics
View original postHy4 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: 63.3% 5. MiMo V2.6 Flash RL: 57.4% Hy 4 is also the top open-weights model in every APEX-Agents domain: Management Consultant: 85.6% Investment Banking Analyst: 75.3% Corporate Lawyer: 71.9% Congrats to @TencentHunyuan. See the full leaderboard: https://t.co/JU07IwL0fQ
View original
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: 63.3% 5. MiMo V2.6 Flash RL: 57.4% Hy 4 is also the top open-weights model in every APEX-Agents domain: Management Consultant: 85.6% Investment Banking Analyst: 75.3% Corporate Lawyer: 71.9% Congrats to @TencentHunyuan. See the full leaderboard: https://t.co/JU07IwL0fQ
Body
#1 open-weights model on APEX-Agents 🙌