XSCT Bench
在开始构建之前,先找到让产品成立的模型。XSCT Bench 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。
https://xsct.ai/Opens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://xsct.ai/mcpWe add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 18, 2026 · xsct.ai
8tools discovered
Get Leaderboard
获取 XSCT Arena 模型排行榜 查询各模型在评测中的综合排名和得分。 评分维度说明: - overall(综合能力): 日常30% + 专业40% + 极限30% 加权平均 - dail…
Get Model Scores
获取模型在各维度的详细评分 了解某个模型在不同测试维度的表现,分析其强项和弱项。 Args: model_name: 模型名称,支持模糊匹配(如 "gemini"、"gpt-4o") t…
Compare Models
对比两个模型在同一测试类型下的表现 并排展示两个模型在各维度的得分差异,帮助用户选择合适的模型。 Args: model_name_a: 第一个模型名称,支持模糊匹配 model_nam…
Search Testcases
搜索测试用例 按关键词、类型、维度搜索测试用例,了解有哪些评测场景。 支持中文关键词智能匹配(如搜索"润色"会匹配到 L-Polish 维度)。 Args: query: 搜索关键词,匹配用例标…
Get Model Case Result
获取模型在某测试用例的完整评测结果 返回模型生成的完整内容、多 Judge 评分详情、各维度得分等信息。 这是查看单个评测结果最详细的工具。 ## 返回内容 1. **模型生成结果**: 完整的生成内…
Get Dimensions
获取所有评测维度列表 查看平台支持的评测维度,了解每个维度包含多少测试用例。 这些维度可用于 search_testcases 的 dimension 参数进行精确筛选。 Args: test_…
Calculate Cost
计算模型使用成本(支持多模型横向对比) 根据各类用量计算使用模型的费用,支持 7 个计费维度和多模型对比。 这是一个强大的成本测算工具,可帮助用户选择最具性价比的模型。 ## 计费维度说明 1. **…
Get Testcase Curl
获取测试用例的 curl 命令 返回可以直接用于测试大模型的 curl 命令,包含完整的 prompt。 你可以复制这个命令,替换 API Key 后直接运行测试。 Args: test_id:…
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brands在开始构建之前,先找到让产品成立的模型。XSCT Bench 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。
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Request removal if you do not want XSCT Arena listed here, or claim the listing if you want to manage it on MCPBundles.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles probed 8 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Request removal from the MCPBundles directory. This does not shut down or change your MCP server — we stop showing it on MCPBundles.
MCPBundles is an independent platform built on the open Model Context Protocol standard. Not affiliated with Anthropic PBC or Claude.