{"slug": "replit-s-vibench-2-0-gives-top-ai-models-a-49-65-whole-product-pass-rate", "title": "Replit's ViBench 2.0 gives top AI models a 49%-65% whole-product pass rate", "summary": "Replit released ViBench 2.0, a benchmark that tests whether AI agents can build 17 complete software products from scratch, adding features in sequence and checking the finished apps in a browser. In Fireworks AI's runs, the top three models passed every test plan in 49% to 65% of builds, according to Replit's announcement and methodology post. Replit published a public harness so teams can reproduce the results, though the vendor-built test suite and partial holdout set limit how broadly the scores apply.", "body_md": "# Replit's ViBench 2.0 gives top AI models a 49%-65% whole-product pass rate\n\n**The benchmark tests agents building 17 products from scratch, adding features in sequence and checking the finished apps in a browser.**\n\n        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)\n        · Published \n\nPrimary source: [replit.com](https://replit.com/blog/vibench-2-long-horizon-software-benchmark)\n\n## Why it matters\n\nWhole-product tests expose failures that feature-by-feature coding benchmarks can miss. ViBench's public harness gives teams a way to reproduce Replit's results, while its vendor-built test suite and partial holdout set are important limits on how broadly to apply the scores.\n\nReplit has released ViBench 2.0, a benchmark that measures whether AI agents can build complete software products feature by feature. In Fireworks AI's runs, the top three models passed every test plan in 49% to 65% of builds, according to [Replit's announcement](https://x.com/Replit/status/2115553116942975013) and its [methodology post](https://replit.com/blog/vibench-2-long-horizon-software-benchmark).…\n\nWhen you purchase through links in our articles, [we may earn a small commission](https://runtimewire.com/affiliate-monetization-standards). This doesn’t affect our editorial independence.", "url": "https://wpnews.pro/news/replit-s-vibench-2-0-gives-top-ai-models-a-49-65-whole-product-pass-rate", "canonical_source": "https://runtimewire.com/article/replit-vibench-2-whole-product-benchmark", "published_at": "2026-10-28 22:40:22+00:00", "updated_at": "2026-10-29 00:42:54.654309+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "artificial-intelligence", "developer-tools"], "entities": ["Replit", "ViBench 2.0", "Fireworks AI", "Ryan Merket"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/replit-s-vibench-2-0-gives-top-ai-models-a-49-65-whole-product-pass-rate", "markdown": "https://wpnews.pro/news/replit-s-vibench-2-0-gives-top-ai-models-a-49-65-whole-product-pass-rate.md", "text": "https://wpnews.pro/news/replit-s-vibench-2-0-gives-top-ai-models-a-49-65-whole-product-pass-rate.txt", "jsonld": "https://wpnews.pro/news/replit-s-vibench-2-0-gives-top-ai-models-a-49-65-whole-product-pass-rate.jsonld"}}