{"id":"27d288bc1d0e","page":"/c/27d288bc1d0e/","topic":"MMMU-Pro Benchmark Results","publisher":"@ArtificialAnlys","official":false,"platform":"X","publishedAt":"2026-03-03T17:16:26.000Z","model":"Gemini 3","form":"benchmark-bars","metrics":{"views":3694,"likes":30,"reposts":0,"quotes":0,"replies":1,"saves":4},"readAt":"2026-10-12T21:30:08.589Z","chartsInPost":1,"score":30,"scoreWeights":{"views":0.4,"likes":0.3,"eng":0.15,"save":0.15},"quadrant":"loved","ranks":{"score":{"industry":{"n":916,"of":1162},"company":{"n":309,"of":491}},"views":{"industry":{"n":1004,"of":1162},"company":{"n":376,"of":491}},"likes":{"industry":{"n":956,"of":1162},"company":{"n":342,"of":491}},"eng":{"industry":{"n":459,"of":1162},"company":{"n":232,"of":491}},"save":{"industry":{"n":381,"of":1162},"company":{"n":177,"of":491}}},"percentiles":{"industry":{"views":0.1364027538726334,"likes":0.17771084337349397,"eng":0.6054216867469879,"save":0.6725473321858864},"company":{"views":0.23523421588594703,"likes":0.3034623217922607,"eng":0.5285132382892057,"save":0.6405295315682281}},"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":215,"views":44446,"eng":0.007500781331388686}},"ratios":{"vsCompanyViews":0.32332603938730853,"vsCompanyLikes":0.38461538461538464,"viewsPerFollower":null,"viewsPerDay":16.551945095429627},"followers":null,"reads":[{"at":"2026-10-12T15:22:05.444Z","views":3694,"likes":30,"reposts":0,"quotes":0,"replies":1,"saves":4,"source":"x-search-cache"}],"chartData":"/api/charts/27d288bc1d0e.json","copy":{"en":{"why":[{"factor":"reach-vs-company","text":"Its 3.7K views sit at 0.32x @ArtificialAnlys's median post, ranking #376 of 491 @ArtificialAnlys posts."},{"factor":"rank","text":"A score of 30 places it #916 of 1,162 AI chart posts and #309 of 491 @ArtificialAnlys posts."},{"factor":"launch-day","text":"It was one of 4 posts from this account that day, ranking #3 of 4 by views."}],"verdict":"The post sits in the Small but loved quadrant, at #916 of 1,162 AI chart posts.","news":{"headline":"@ArtificialAnlys posts MMMU-Pro benchmark chart with 17 models","dek":"A 17-model MMMU-Pro bar chart drew 3.7K views and a 0.84% engagement rate, above the AI chart median.","what":"@ArtificialAnlys published a benchmark bar chart of MMMU-Pro results on March 3, 2026. It was one of 4 posts from the account that day, alongside Artificial Analysis Intelligence Index v4.0, Output Tokens per Second, and Cost to Run Artificial Analysis Intelligence Index.","numbers":"The post reached 3.7K views, ranking #1,004 of 1,162 AI chart posts and #376 of 491 @ArtificialAnlys posts. Its score of 30 ranks #916 of 1,162 AI chart posts.","lesson":"The chart shows 17 models, and the post drew 3.7K views against a 39.9K median among AI chart posts. A 17-model comparison at 0.32x the company median shows the model count did not carry the reach.","implication":"At #309 of 491 @ArtificialAnlys posts, this chart sits below the account's own median. The 0.32x gap to the company median of 11.4K views marks it as a low-reach post for this publisher."}},"zh":{"why":[{"factor":"reach-vs-company","text":"浏览量3694，低于@ArtificialAnlys中位数1.1万的0.32倍，在491条帖子中排第376。"},{"factor":"rank","text":"得分30，在1162条AI图表帖中排第916，在491条帖子中排第309。"},{"factor":"launch-day","text":"发布当天4条帖子中排第3，浏览量低于同日最大帖3.8万。"}],"verdict":"范围小，但很受欢迎：浏览量低于中位数，互动率不低于中位数，得分排第916。","news":{"headline":"@ArtificialAnlys的MMMU-Pro基准图浏览量排第1004","dek":"浏览量3694，互动率0.84%，收藏率0.11%。","what":"2026年3月3日，@ArtificialAnlys发布1张MMMU-Pro基准柱状图，展示17个模型的得分。同日还有3条帖子，分别关于Artificial Analysis Intelligence Index v4.0、Output Tokens per Second和Cost to Run Artificial Analysis Intelligence Index。","numbers":"浏览量3694，在1162条AI图表帖中排第1004，低于中位数4万。得分30，在1162条中排第916。","lesson":"浏览量3694，是@ArtificialAnlys中位数1.1万的0.32倍，在491条帖子中排第376。收藏率0.11%，互动率0.84%，范围小但互动不低。","implication":"该帖浏览量低于自家中位数，但互动率0.84%不低于AI图表帖中位数，属于范围小但受欢迎。后续3月6日CritPt Benchmark帖子浏览量11.4万，显示同类基准图有更大潜力。"}},"lane":"en:amd/DeepSeek-V4.1-Flash zh:amd/DeepSeek-V4-Flash","checkedAt":"2026-10-13T21:03:21.893Z"}}