{"id":"577d7d40ae9e","page":"/c/577d7d40ae9e/","topic":"CriterPT and Humanity's Last Exam Benchmark Results","publisher":"@ArtificialAnlys","official":false,"platform":"X","publishedAt":"2026-05-28T21:54:42.000Z","model":"Claude Opus 4","form":"leaderboard","metrics":{"views":4592,"likes":68,"reposts":4,"quotes":0,"replies":1,"saves":5},"readAt":"2026-10-12T21:30:08.589Z","chartsInPost":1,"score":40,"scoreWeights":{"views":0.4,"likes":0.3,"eng":0.15,"save":0.15},"quadrant":"loved","ranks":{"score":{"industry":{"n":759,"of":1162},"company":{"n":223,"of":491}},"views":{"industry":{"n":970,"of":1162},"company":{"n":350,"of":491}},"likes":{"industry":{"n":818,"of":1162},"company":{"n":254,"of":491}},"eng":{"industry":{"n":80,"of":1162},"company":{"n":38,"of":491}},"save":{"industry":{"n":379,"of":1162},"company":{"n":176,"of":491}}},"percentiles":{"industry":{"views":0.16566265060240964,"likes":0.29690189328743544,"eng":0.9315834767641996,"save":0.6742685025817556},"company":{"views":0.28818737270875766,"likes":0.48370672097759676,"eng":0.9236252545824847,"save":0.6425661914460286}},"peers":{"industry":1162,"company":491,"companyName":"@artificialanlys"},"medians":{"industry":{"views":39945,"likes":289,"eng":0.007331788144862199,"save":0.0007642791742968587},"company":{"views":11425,"likes":78,"eng":0.008185850825444735,"save":0.0007598784194528875},"form":{"n":107,"views":45263,"eng":0.006913658433607768}},"ratios":{"vsCompanyViews":0.40192560175054703,"vsCompanyLikes":0.8717948717948718,"viewsPerFollower":null,"viewsPerDay":33.52242095023779},"followers":null,"reads":[{"at":"2026-10-12T15:19:23.813Z","views":4592,"likes":68,"reposts":4,"quotes":0,"replies":1,"saves":5,"source":"x-search-cache"}],"chartData":"/api/charts/577d7d40ae9e.json","copy":{"en":{"why":[{"factor":"engagement","text":"Its 1.59% engagement rate sits at the 93rd percentile among AI chart posts, against a 0.73% median."},{"factor":"reach-vs-company","text":"At 4.6K views it runs 0.40x this company's 11.4K median, ranking #350 of 491 @ArtificialAnlys posts."},{"factor":"launch-day","text":"It was the #2 of 2 posts from this account that day by views."}],"verdict":"The post sits in the Small but loved quadrant, with a score rank of #759 of 1,162 AI chart posts.","news":{"headline":"@ArtificialAnlys posts CriterPT and Humanity's Last Exam leaderboard","dek":"A 25-model leaderboard drew 4.6K views and a 1.59% engagement rate, landing in the Small but loved quadrant.","what":"On May 28, 2026, @ArtificialAnlys published a leaderboard on CriterPT and Humanity's Last Exam benchmark results. It was one of 2 posts from this account that day, alongside Artificial Analysis Intelligence Index v4.0.","numbers":"The post reached 4.6K views, ranking #970 of 1,162 AI chart posts and #350 of 491 @ArtificialAnlys posts. Its score rank is #759 of 1,162 AI chart posts.","lesson":"A 25-model leaderboard drew a 1.59% engagement rate, the 93rd percentile among AI chart posts. The same chart type at 4.6K views shows the save rate of 0.11%.","implication":"At #223 of 491 @ArtificialAnlys posts by score, this chart sits below the account's own 11.4K median views. The 0.40x gap to that median is the measured distance for this publisher's chart posts."}},"zh":{"why":[{"factor":"engagement","text":"互动率1.59%达第93百分位，是AI图表帖中位数0.73%的2倍以上"},{"factor":"reach-vs-company","text":"浏览量4592仅为本账号中位数1.1万的0.40倍，排第350位"},{"factor":"launch-day","text":"发布当天2条帖子中排第2，被同日另一帖5.3万浏览量压制"}],"verdict":"范围小但很受欢迎，在1162条AI图表帖中排第759","news":{"headline":"@ArtificialAnlys发CriterPT榜单，互动高但流量低","dek":"互动率前10%，浏览量低于中位数","what":"2026年5月28日发布1张排行榜图表，展示CriterPT和Humanity's Last Exam基准结果，列出25个模型。同日另有1条关于Artificial Analysis Intelligence Index v4.0的帖子。","numbers":"浏览量4592，在1162条AI图表帖中排第970，低于中位数4万。互动率1.59%，在1162条中排第80，高于中位数0.73%。","lesson":"高互动率（第93百分位）未能弥补低浏览量（第970位），帖子处于范围小但很受欢迎的象限，得分40在1162条中排第759。","implication":"对本账号而言，该帖浏览量排第350，低于自身中位数1.1万，但互动率高于自身中位数0.82%，说明小众内容能吸引忠实读者。"}},"lane":"en:amd/DeepSeek-V4.1-Flash zh:amd/DeepSeek-V4-Flash","checkedAt":"2026-10-13T20:46:38.021Z"}}