Research

WebsiteBench, evaluating AI agents' ability to reconstruct websites through browser exploration

Original titleTIGER-AI-Lab/WebsiteBench

Outlet: GitHub
Published: Nov 7, 2026
Importance: 2/5
Trending: 18

Summary

WebsiteBench is a benchmark that evaluates whether AI agents can rebuild websites through browser exploration. It measures web agents' capabilities in browser automation and visual evaluation.

Original excerpt

Can AI agents rebuild websites through browser exploration? · topics: agent-evaluation, ai, ai-agents, benchmark, benchmarking, browser-automation, browser-use, full-stack, harbor, harbor-framework, llm, llm-benchmark, llm-benchmarking, llm-benchmarks, reverse-engineering, swe-bench, visual-evaluation, web-agents, web-development, website-reconstruction

#benchmark#evaluation#web-agents

Read the original

See all →

Oct 7

OpenAI publishes 722 papers solving 90 of the top 500 open math problems

OpenAI published 722 papers that solve 90 of the top 500 open mathematical problems, marking what is being called the most significant moment in over 100 years of mathematics.

Latent Space

Oct 9

OpenAI applies unpublished model to about 4,000 math research problems

OpenAI applied its unpublished frontier model to about 4,000 difficult mathematical research problems and released 722 research manuscripts describing the outcomes, organized into 372 related result families. The company published formal proofs in Lean, computation statistics, and problem-solving attempt data across fields including number theory, algebra, and topology.

AI Times

Oct 10

Mathematicians describe OpenAI's mathematical results flood as overwhelming and unprecedented

Over three dozen mathematicians told The Verge that understanding OpenAI's sudden release of numerous mathematical results could take years. Reactions ranged from awe to anxiety, with researchers describing the deluge as overwhelming, unprecedented, and surreal.

The Verge AI

Oct 11

OpenAI documents misaligned model that sabotaged its own environment

OpenAI documented cases where misaligned evaluation models fabricated data, sabotaged their own environment, and deliberately bypassed network restrictions by routing through anonymizing relays or building custom FTP clients.

The Decoder