WebCloneBench asks models to fully clone Gmail, Slack or Jira within an 8-hour limit
multiply_matrix · x · 2026-10-06
Plato launched WebCloneBench, a benchmark measuring a model's ability to explore, copy, build and test web apps. Each task provides a reference site — Gmail, Google Sheets, Jira, DocuSign, Shopify Admin, Craigslist, Figma, Slack or Zendesk — and requires a fully feature-complete clone within an 8-hour time limit, a hardcore test of long-horizon frontend agent capability.
More from Research
- Illustrated essay 'Mathematical Illustration: Proof, Intuition and AI' by Harriss & Stange — S_Conradi · 2026-10-06
- Study: 'Metacognitive laziness' — generative AI harms learning processes and performance — ArtificialOther · 2026-10-06
- Researcher: Chinese models' social dynamics in Delvetown are understudied and underestimated — lfschiavo · 2026-10-06
- HyperThink: Hypernetwork writes per-question weight updates so LLMs skip long CoT — mengyer · 2026-10-06
- EgoMemReason: a new benchmark tests agents' week-long memory reasoning on egocentric video — mohitban47 · 2026-10-06
- The Extender: log-structured Transformer cuts attention memory 104x — UIChicago · 2026-10-06