Key Info

Tencent's Hy4 placed #4 among 23 models evaluated on OpenDesign's benchmark of real-world design tasks derived from user requests, scoring just 0.1 points behind GPT-6.1 Sol at an estimated 41% lower cost.

Highlights

  • Benchmark covers 23 models tested on real-world design tasks based on user requests
  • Hy4 ranks #4 overall
  • Hy4 trails GPT-6.1 Sol by only 0.1 points
  • Estimated cost is 41% lower than GPT-6.1 Sol
  • Hy4 is now available on OpenDesign