https://www.ianww.com/_next/static/chunks/pages/llm-tools-b74eea1595c7157f.js

1(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[11],{7706:function(e,t,o){(window.__NEXT_P=window.__NEXT_P||[]).push(["/llm-tools",function(){return o(2755)}])},2755:function(e,t,o){"use strict";o.r(t);var r=o(4637),n=o(9496),a=o(5337),i=o.n(a),s=o(3949),l=o.n(s);function c(e,t){(null==t||t>e.length)&&(t=e.length);for(var o=0,r=new Array(t);o<t;o++)r[o]=e[o];return r}function d(e,t){return function(e){if(Array.isArray(e))return e}(e)||function(e,t){var o=null==e?null:"undefined"!==typeof Symbol&&e[Symbol.iterator]||e["@@iterator"];if(null!=o){var r,n,a=[],i=!0,s=!1;try{for(o=o.call(e);!(i=(r=o.next()).done)&&(a.push(r.value),!t||a.length!==t);i=!0);}catch(l){s=!0,n=l}finally{try{i||null==o.return||o.return()}finally{if(s)throw n}}return a}}(e,t)||function(e,t){if(!e)return;if("string"===typeof e)return c(e,t);var o=Object.prototype.toString.call(e).slice(8,-1);"Object"===o&&e.constructor&&(o=e.constructor.name);if("Map"===o||"Set"===o)return Array.from(o);if("Arguments"===o||/^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(o))return c(e,t)}(e,t)||function(){throw new TypeError("Invalid attempt to destructure non-iterable instance.\\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method.")}()}var u=function(e){var t=e.children,o=e.text,a=d(n.useState(!1),2),i=a[0],s=a[1];return(0,r.jsxs)("div",{onMouseEnter:function(){return s(!0)},onMouseLeave:function(){return s(!1)},className:l().tooltipContainer,children:[t,i&&(0,r.jsx)("div",{className:l().tooltip,children:o})]})};t.default=function(){var e=d(n.useState("all-data"),2),t=e[0],o=e[1];n.useEffect((function(){var e=window.location.hash.replace("#","");e&&o(e)}),[]),n.useEffect((function(){var e=function(){o(window.location.hash.replace("#","")||"all-data")};return window.addEventListener("hashchange",e,!1),function(){window.removeEventListener("hashchange",e,!1)}}),[]);var a=function(e){window.location.hash=e};return(0,r.jsxs)(r.Fragment,{children:[(0,r.jsxs)(i(),{children:[(0,r.jsx)("title",{children:"List of LLM eval tools"}),(0,r.jsx)("meta",{name:"description",content:"Spreadsheet of 50+ LLM evaluation tools designed to test and improve language model prompts."}),(0,r.jsx)("meta",{property:"og:title",content:"LLM eval tools spreadsheet"}),(0,r.jsx)("meta",{property:"og:image",content:"/images/llm-tools.png"}),(0,r.jsx)("meta",{property:"og:description",content:"Spreadsheet of 50+ LLM evaluation tools for testing models and improving prompts."}),(0,r.jsx)("meta",{property:"og:type",content:"website"}),(0,r.jsx)("meta",{property:"og:image:alt",content:"LLM eval tools spreadsheet"}),(0,r.jsx)("meta",{property:"twitter:card",content:"summary_large_image"}),(0,r.jsx)("meta",{property:"twitter:title",content:"LLM eval tools spreadsheet"}),(0,r.jsx)("meta",{property:"twitter:description",content:"Spreadsheet of 50+ LLM evaluation tools for testing models and improving prompts."}),(0,r.jsx)("meta",{property:"twitter:image",content:"/images/llm-tools.png"}),(0,r.jsx)("meta",{property:"twitter:image:alt",content:"LLM eval tools spreadsheet"})]}),(0,r.jsxs)("div",{className:l().container,children:[(0,r.jsx)("h1",{children:"LLM evaluation tools"}),(0,r.jsxs)("p",{children:["A collection of LLM evaluation tools for testing models and improving prompts. Submit new tools ",(0,r.jsx)("a",{rel:"noreferer noopener",href:"https://airtable.com/appVr5xALHf6UbPc6/pag8n9Sa2di3l6XDm/form",children:"here"}),"."]}),(0,r.jsx)("div",{children:(0,r.jsxs)("details",{children:[(0,r.jsx)("summary",{children:"Why do evals matter?"}),(0,r.jsx)("p",{children:"Defining and measuring model performance can help you understand how to improve your model, prompts, and RAG flow."}),(0,r.jsx)("p",{children:'By continuously testing and setting guardrail metrics, you can avoid the feeling of "trial and error" when developing, improving, and debugging your LLM app.'}),(0,r.jsx)("p",{children:"The goal: deploy changes with confidence that you're improving the overall system!"})]})}),(0,r.jsxs)("div",{className:l().tabs,children:[(0,r.jsx)("button",{onClick:function(){return a("all-data")},className:"all-data"===t?l().active:"",children:"All"}),(0,r.jsx)(u,{text:"Fully open-source eval tools (including SDK, UI, and backend)",children:(0,r.jsx)("button",{onClick:function(){return a("open-source")},className:"open-source"===t?l().active:"",children:"Open Source"})}),(0,r.jsx)(u,{text:"Commercial eval tools",children:(0,r.jsx)("button",{onClick:function(){return a("commercial")},className:"commercial"===t?l().active:"",children:"Commercial"})}),(0,r.jsx)(u,{text:"Tools that offer a visual interface",children:(0,r.jsx)("button",{onClick:function(){return a("has-ui")},className:"has-ui"===t?l().active:"",children:"Has UI"})}),(0,r.jsx)(u,{text:"Tools that offer an SDK for integration",children:(0,r.jsx)("button",{onClick:function(){return a("has-sdk")},className:"has-sdk"===t?l().active:"",children:"Has SDK"})}),(0,r.jsx)(u,{text:"Tools from YC companies",children:(0,r.jsx)("button",{onClick:function(){return a("is-yc")},className:"is-yc"===t?l().active:"",children:"YC Companies"})})]}),(0,r.jsxs)("div",{className:l().tabContent,children:["all-data"===t&&(0,r.jsx)("iframe",{src:"https://airtable.com/embed/appVr5xALHf6UbPc6/shr1TTFFtKKX18lL3?backgroundColor=gray&viewControl

1s=on",width:"100%",height:"1000"}),"open-source"===t&&(0,r.jsx)("iframe",{src:"https://airtable.com/embed/appVr5xALHf6UbPc6/shrC4UBIwIeNxKzjy?backgroundColor=gray&viewControls=on",width:"100%",height:"1000"}),"commercial"===t&&(0,r.jsx)("iframe",{src:"https://airtable.com/embed/appVr5xALHf6UbPc6/shrh1bOaNBsGWd3dx?backgroundColor=gray&viewControls=on",width:"100%",height:"1000"}),"has-ui"===t&&(0,r.jsx)("iframe",{src:"https://airtable.com/embed/appVr5xALHf6UbPc6/shrw49SH5JQ1rWD4A?backgroundColor=gray&viewControls=on",width:"100%",height:"1000"}),"has-sdk"===t&&(0,r.jsx)("iframe",{src:"https://airtable.com/embed/appVr5xALHf6UbPc6/shrSCk744yrg9ez66?backgroundColor=gray&viewControls=on",width:"100%",height:"1000"}),"is-yc"===t&&(0,r.jsx)("iframe",{src:"https://airtable.com/embed/appVr5xALHf6UbPc6/shrcxCyg6HN0Etz0s?backgroundColor=gray&viewControls=on",width:"100%",height:"1000"})]})]})]})}},3949:function(e){e.exports={container:"LlmTools_container__tripm",active:"LlmTools_active__HovwH",tooltipContainer:"LlmTools_tooltipContainer__uHagL",tooltip:"LlmTools_tooltip___Ij7D"}}},function(e){e.O(0,[774,888,179],(function(){return t=7706,e(e.s=t);var t}));var t=e.O();_N_E=t}]);