{"id":"f726707ce980","page":"/c/f726707ce980/","topic":"Agents' Last Exam","publisher":"OpenAI","official":true,"platform":"X","publishedAt":"2026-07-09T17:30:38.000Z","model":"GPT-5","form":"line","metrics":{"views":162721,"likes":1190,"reposts":113,"quotes":52,"replies":28,"saves":121},"readAt":"2026-10-13T19:17:33.947Z","chartsInPost":1,"score":70,"scoreWeights":{"views":0.4,"likes":0.3,"eng":0.15,"save":0.15},"quadrant":"hit","ranks":{"score":{"industry":{"n":223,"of":1162},"company":{"n":16,"of":74}},"views":{"industry":{"n":295,"of":1162},"company":{"n":37,"of":74}},"likes":{"industry":{"n":239,"of":1162},"company":{"n":26,"of":74}},"eng":{"industry":{"n":442,"of":1162},"company":{"n":13,"of":74}},"save":{"industry":{"n":594,"of":1162},"company":{"n":16,"of":74}}},"percentiles":{"industry":{"views":0.7465576592082617,"likes":0.794750430292599,"eng":0.6200516351118761,"save":0.4892426850258176},"company":{"views":0.5067567567567568,"likes":0.6554054054054054,"eng":0.831081081081081,"save":0.7905405405405406}},"peers":{"industry":1162,"company":74,"companyName":"OpenAI"},"medians":{"industry":{"views":39945,"likes":289,"eng":0.007331788144862199,"save":0.0007642791742968587},"company":{"views":161517.5,"likes":714.5,"eng":0.005359315036129835,"save":0.00048697197603225794},"form":{"n":68,"views":73692,"eng":0.006568549381975924}},"ratios":{"vsCompanyViews":1.0074512049777888,"vsCompanyLikes":1.6655003498950316,"viewsPerFollower":0.029950162514340448,"viewsPerDay":1693.7002928105037},"followers":5433059,"reads":[{"at":"2026-10-12T15:16:15.713Z","views":162691,"likes":1189,"reposts":113,"quotes":52,"replies":28,"saves":121,"source":"x-search-cache"},{"at":"2026-10-12T15:29:38.921Z","views":162691,"likes":1189,"reposts":113,"quotes":52,"replies":28,"saves":121,"source":"x-search-cache"},{"at":"2026-10-13T19:17:33.947Z","views":162721,"likes":1190,"reposts":113,"quotes":52,"replies":28,"saves":121,"source":"bird-read"}],"chartData":"/api/charts/f726707ce980.json","copy":{"en":{"why":[{"factor":"views-per-follower","text":"Its 0.030 views per follower sits at 0.15x the median across posts with known followers, an 18th percentile mark."},{"factor":"rank","text":"The score of 70 lands at #223 of 1,162 AI chart posts and #16 of 74 OpenAI posts."},{"factor":"launch-day","text":"It ranked #2 of 3 posts from this account that day, with 3 posts from this account that day."}],"verdict":"The post sits in the Reached and resonated quadrant at #223 of 1,162 AI chart posts.","news":{"headline":"OpenAI posts Agents' Last Exam line chart on July 9, 2026","dek":"The line chart plots AI model performance against API cost, drawing 163K views and a 0.85% engagement rate.","what":"OpenAI published a line chart on July 9, 2026, covering Agents' Last Exam and AI model performance vs API cost. It came with 2 other posts from this account that day, on Artificial Analysis Coding Agent Index v1.1 and SEC-Bench Pro Multi-Agent Performance.","numbers":"The post drew 163K views, ranking #295 of 1,162 AI chart posts, against a median of 39.9K views among AI chart posts. Its score of 70 placed it at #223 of 1,162 AI chart posts and #16 of 74 OpenAI posts.","lesson":"The chart shows 7 models on a line chart, and the post earned a 0.074% save rate against a 0.85% engagement rate. A 7-model line chart at that save rate is what readers kept from this post.","implication":"At #16 of 74 OpenAI posts, this chart sits well inside the account's own range, while its 0.030 views per follower is 0.15x the median across posts with known followers. The gap between its #223 of 1,162 AI chart posts score rank and its 18th percentile views-per-follower mark is the measured spread."}},"zh":{"why":[{"factor":"views-per-follower","text":"浏览量16.3万，粉丝543万，单帖浏览粉丝比0.030，仅为中位数0.20的0.15倍，排第18百分位。"},{"factor":"rank","text":"综合得分70，在1162条AI图表帖中排第223，在OpenAI的74条帖子中排第16，高于中位。"},{"factor":"launch-day","text":"发布当天OpenAI共发3条，本帖子浏览量在3条中排第2，处于中间水平。"}],"verdict":"传得远，也打动人，在1162条AI图表帖中排第223。","news":{"headline":"OpenAI图表帖浏览量16.3万","dek":"互动率0.85%，收藏率0.074%，综合得分70。","what":"OpenAI于2026年7月9日发布1张图表，展示7个模型的对比。当天另有2条帖子，分别关于Artificial Analysis Coding Agent Index v1.1和SEC-Bench Pro Multi-Agent Performance。","numbers":"浏览量16.3万，在1162条AI图表帖中排第295，高于中位数4万。点赞1190，互动率0.85%。","lesson":"浏览量16.3万，但浏览粉丝比0.030仅为中位数0.20的0.15倍，排第18百分位。粉丝基数大，单帖触达效率低。","implication":"在OpenAI的74条帖子中排第16，但浏览粉丝比低于中位数，说明粉丝转化有限。发布当天3条帖子中排第2，非当日最热。"}},"lane":"en:amd/DeepSeek-V4.1-Flash zh:amd/DeepSeek-V4-Flash","checkedAt":"2026-10-13T21:09:01.406Z"}}