{"id":"bf72415d-8157-429e-9e67-26cbb2e59a4f","kind":"companies","code":"UB-C13307","name":"XSCT Bench","nameBasis":"source-english","summary":"Find the model that makes your product work","description":"Before you build, first find the model that makes the product work. Xiaoshan Chuti provides test data of GPT-4o, Claude, Gemini, Qwen, DeepSeek, and 30+ mainstream LLMs in real product scenes—helping you decide on capability, effect, and cost dimensions.","country":null,"category":null,"originalName":"XSCT Bench","eventDate":null,"website":"https://xsct.ai/","sourceUpdatedAt":"2026-10-26T00:00:00.000Z","englishUpdatedAt":"2026-11-01T02:31:49.023Z","reviewedAt":"2026-11-01T02:31:49.023Z","snapshotAt":"2026-11-01T00:40:31.077Z","sourceHash":"c1592a18a27ae4e9909ad5224e1c6b965418467c14aa762f86fa47f4c8ec5454","companyId":null,"foundedYear":null,"logoUrl":null,"originalText":"找到让你产品成立的那个模型\n\n在开始构建之前，先找到让产品成立的模型。小山出题提供 GPT-4o、Claude、Gemini、Qwen、DeepSeek 等 30+ 主流大模型在真实产品场景下的测试数据，帮你在能力、效果、成本三个维度做出选型决策。","sources":[],"related":[{"id":"3efea13e-30b1-44b3-aa06-d7deebafa36f","kind":"products","code":"UB-D7992","name":"XSCT Bench","nameBasis":"original-brand","summary":"Scenario-based model selection platform for AI product implementation The core problem we want to solve is the gap from \"score\" to \"selection\" There is a structural problem in the field of large-scale model evaluation: there is an insurmountable gap between the existing list design and the decision-making information that users really need. The purpose of users using the list is to make selection decisions - to select the most suitable model for a specific product or work scenario. However, the existing list gives a comprehensive score that is divorced from the scenario: After reading a bunch of evaluation lists, the comprehensive score of Model A is 92, and the comprehensive score of Model B is 88. But what you want to do is to generate a marketing copywriting product, which one should you choose? Model A has stronger mathematical capabilities, but your scenario doesn’t require mathematics at all. Model B is half the price and has better creative writing skills, but it’s not obvious from the list. This is the problem we want to solve: allowing you to make “prescribed medicines” based on real scenarios, rather than blindly pursuing “the strongest”.","description":"Scenario-based model selection platform for AI product implementation The core problem we want to solve is the gap from \"score\" to \"selection\" There is a structural problem in the field of large-scale model evaluation: there is an insurmountable gap between the existing list design and the decision-making information that users really need. The purpose of users using the list is to make selection decisions - to select the most suitable model for a specific product or work scenario. However, the existing list gives a comprehensive score that is divorced from the scenario: After reading a bunch of evaluation lists, the comprehensive score of Model A is 92, and the comprehensive score of Model B is 88. But what you want to do is to generate a marketing copywriting product, which one should you choose? Model A has stronger mathematical capabilities, but your scenario doesn’t require mathematics at all. Model B is half the price and has better creative writing skills, but it’s not obvious from the list. This is the problem we want to solve: allowing you to make “prescribed medicines” based on real scenarios, rather than blindly pursuing “the strongest”.","country":null,"category":null,"originalName":"XSCT Bench","eventDate":null,"website":null,"sourceUpdatedAt":"2026-10-26T21:00:22.555Z","englishUpdatedAt":"2026-10-28T00:56:06.878Z","reviewedAt":"2026-10-28T00:56:06.878Z","snapshotAt":"2026-10-28T00:47:51.550Z","sourceHash":"daf10f4329dde161614e919550a4486a71e6211484bac560e3c16d37095b1757","companyId":"bf72415d-8157-429e-9e67-26cbb2e59a4f","foundedYear":null,"logoUrl":null,"path":"/products/xsct-bench"}],"finance":{"funding":{"metric":"funding","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[],"totalRaised":null},"valuation":{"metric":"valuation","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[]},"revenue":{"metric":"revenue","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[]}},"events":[],"team":[],"productsRelated":[{"id":"3efea13e-30b1-44b3-aa06-d7deebafa36f","kind":"products","code":"UB-D7992","name":"XSCT Bench","nameBasis":"original-brand","summary":"Scenario-based model selection platform for AI product implementation The core problem we want to solve is the gap from \"score\" to \"selection\" There is a structural problem in the field of large-scale model evaluation: there is an insurmountable gap between the existing list design and the decision-making information that users really need. The purpose of users using the list is to make selection decisions - to select the most suitable model for a specific product or work scenario. However, the existing list gives a comprehensive score that is divorced from the scenario: After reading a bunch of evaluation lists, the comprehensive score of Model A is 92, and the comprehensive score of Model B is 88. But what you want to do is to generate a marketing copywriting product, which one should you choose? Model A has stronger mathematical capabilities, but your scenario doesn’t require mathematics at all. Model B is half the price and has better creative writing skills, but it’s not obvious from the list. This is the problem we want to solve: allowing you to make “prescribed medicines” based on real scenarios, rather than blindly pursuing “the strongest”.","description":"Scenario-based model selection platform for AI product implementation The core problem we want to solve is the gap from \"score\" to \"selection\" There is a structural problem in the field of large-scale model evaluation: there is an insurmountable gap between the existing list design and the decision-making information that users really need. The purpose of users using the list is to make selection decisions - to select the most suitable model for a specific product or work scenario. However, the existing list gives a comprehensive score that is divorced from the scenario: After reading a bunch of evaluation lists, the comprehensive score of Model A is 92, and the comprehensive score of Model B is 88. But what you want to do is to generate a marketing copywriting product, which one should you choose? Model A has stronger mathematical capabilities, but your scenario doesn’t require mathematics at all. Model B is half the price and has better creative writing skills, but it’s not obvious from the list. This is the problem we want to solve: allowing you to make “prescribed medicines” based on real scenarios, rather than blindly pursuing “the strongest”.","country":null,"category":null,"originalName":"XSCT Bench","eventDate":null,"website":null,"sourceUpdatedAt":"2026-10-26T21:00:22.555Z","englishUpdatedAt":"2026-10-28T00:56:06.878Z","reviewedAt":"2026-10-28T00:56:06.878Z","snapshotAt":"2026-10-28T00:47:51.550Z","sourceHash":"daf10f4329dde161614e919550a4486a71e6211484bac560e3c16d37095b1757","companyId":"bf72415d-8157-429e-9e67-26cbb2e59a4f","foundedYear":null,"logoUrl":null,"path":"/products/xsct-bench"}],"investors":[],"path":"/companies/xsct-bench","structured":{"city":null,"country":null,"location":null,"role":null,"category":null,"company":null},"definition":"XSCT Bench is a company.","summaryBasis":"translated","thin":false,"canonical":"https://uniquebase.ai/companies/xsct-bench"}