Skip to content
Hot storiesContinuously updated

Replit团队推出长程软件构建评测基准ViBench 2.0

1 reports1 reporting sourcesUpdated 8 hours ago

Start here

AI overview

2026年11月5日，Replit团队在arXiv发布长程软件构建评测基准ViBench 2.0。该评测基准涵盖17个全栈Web产品以及241个功能请求，主要针对长程软件构建场景，用于评估代码智能体端到端交付完整软件的能力。目前该基准已正式对外推出，为代码智能体在复杂软件工程交付维度的能力评估提供了新参考。

AI-generated from reports · Updated 8 hours ago

Latest developmentsNov 5 13:00
Replit团队推出ViBench 2.0基准，评估代码智能体端到端交付完整软件的能力。

Report timeline

Follow the reports to see different sides of the story.

Nov 5
  1. arXiv 人工智能Selected
    ViBench 2.0 Benchmark Released: Evaluating Code Agents' End-to-End Delivery Capabilities for Long-Horizon Software Development

    The Replit team has introduced ViBench 2.0, a long-horizon software development benchmark spanning 17 full-stack web products and 241 feature requests to evaluate models' capabilities in delivering complete software end-to-end.

Story heat trend

Current heat 8·Comparable peak 10（Nov 5 14:00）·Comparable change, last 24 hours–

02.557.510Nov5Nov5Nov5Nov5

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.