English(EN) ViBench 2.0: A Benchmark for Long-Horizon Software Building

Replit 发布 ViBench 2.0，用于长周期人工智能软件开发

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 18:50

Replit 发布了 ViBench 2.0，这是一个旨在评估人工智能模型在长周期软件开发任务方面能力的新基准测试。与以往专注于特定编码问题的基准测试不同，ViBench 2.0 要求人工智能代理从头开始构建整个产品，并随着时间的推移逐步添加功能。该基准测试包含十七个不同的产品和 241 项功能请求，表现最佳的模型如 GPT-6.1 Sol、GPT-6 Astra 和 Opus 5.5 在测试计划上的成功率介于 49-65% 之间。 AI

影响为评估人工智能处理复杂、多阶段软件开发项目的能力树立了新标准。

排序理由用于评估人工智能模型在复杂软件开发任务方面能力的新基准测试。[lever_c_demoted from research: ic=1 ai=1.0]

在 Replit blog 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 用于评估人工智能模型在复杂软件开发任务方面能力的新基准测试。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: product, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

Replit blog TIER_1 English(EN) · 2026-10-28 18:50

ViBench 2.0：面向长周期软件构建的基准测试

Today we’re releasing ViBench 2.0, a benchmark for long-horizon software development. It joins the Specialized Intelligence Index (SII) from Fireworks [1], our partner for open-weight model inference and training. The SII brings together practitioner-built benchmarks to compare o…

本文如何被排名

报道来源 [1]

ViBench 2.0：面向长周期软件构建的基准测试

相关实体

相关话题