Tencent Hy4 ranks #4 on OpenDesign design benchmark, 0.1 pt behind GPT-6.1 Sol at 41% lower cost
ShunyuYao12 · x · 2026-11-06
OpenDesign tested 23 models on real-world design tasks: Tencent Hunyuan's Hy4 scored 90.0/100, ranking #4 and just 0.1 points behind GPT-6.1 Sol (90.1) at an estimated 41% lower cost ($0.227 per artifact). Kimi K3.1 Pro leads with 91.0, followed by GPT-6.1 Terra at 90.3. Scores combine design quality (70) and requirements fulfillment (30), with costs estimated from recorded token usage (Nov 2026 data).
More from Models
- Custom GPTs die Dec 11: if you use someone else's GPT, you can't migrate it — Ok_Negotiation_2587 · 2026-11-06
- Kimi K3.1 and Tencent Hy4 accused of gutting cybersecurity skills from open-weight models — Fresh_Sun_1017 · 2026-11-06
- On the METR graph: insiders seeing AECI tasks is weak evidence, not zero evidence — gleech · 2026-11-06
- Daily AI brief: GPT-6.2 imminent, Claude Personal Finance beta, METR says Anthropic progress up 1.9x — testingcatalog · 2026-11-06
- METR report researcher quotes lean bullish: Opus 4.5 coding plus faster experiment cycles — gleech · 2026-11-06
- Epoch AI review: OSWorld tasks are simple, unstable, and barely test GUI use — gleech · 2026-11-06