{"id":"4ad7f9a37842","page":"/c/4ad7f9a37842/","topic":"FrontierMath accuracy comparison of Grok models","publisher":"@EpochAIResearch","official":false,"platform":"X","publishedAt":"2025-04-11T13:24:02.000Z","model":"Grok 3","form":"benchmark-bars","metrics":{"views":3086,"likes":31,"reposts":2,"quotes":2,"replies":2,"saves":3},"readAt":"2026-10-12T21:30:08.589Z","chartsInPost":1,"score":32,"scoreWeights":{"views":0.4,"likes":0.3,"eng":0.15,"save":0.15},"quadrant":"loved","ranks":{"score":{"industry":{"n":878,"of":1162},"company":{"n":48,"of":59}},"views":{"industry":{"n":1034,"of":1162},"company":{"n":39,"of":59}},"likes":{"industry":{"n":948,"of":1162},"company":{"n":45,"of":59}},"eng":{"industry":{"n":199,"of":1162},"company":{"n":37,"of":59}},"save":{"industry":{"n":445,"of":1162},"company":{"n":40,"of":59}}},"percentiles":{"industry":{"views":0.11058519793459552,"likes":0.18416523235800344,"eng":0.8291738382099828,"save":0.6174698795180723},"company":{"views":0.3474576271186441,"likes":0.23728813559322035,"eng":0.3813559322033898,"save":0.3305084745762712}},"peers":{"industry":1162,"company":59,"companyName":"@epochairesearch"},"medians":{"industry":{"views":39945,"likes":289,"eng":0.007331788144862199,"save":0.0007642791742968587},"company":{"views":5278,"likes":63,"eng":0.013723883654240066,"save":0.0012807487454203996},"form":{"n":215,"views":44446,"eng":0.007500781331388686}},"ratios":{"vsCompanyViews":0.5846911708980674,"vsCompanyLikes":0.49206349206349204,"viewsPerFollower":null,"viewsPerDay":5.617675056931772},"followers":null,"reads":[{"at":"2026-10-12T15:42:38.405Z","views":3086,"likes":31,"reposts":2,"quotes":2,"replies":2,"saves":3,"source":"x-search-cache"}],"chartData":"/api/charts/4ad7f9a37842.json","copy":{"en":{"why":[{"factor":"engagement","text":"Its 1.20% engagement rate sits at the 83rd percentile among AI chart posts, against a 0.73% median."},{"factor":"rank","text":"The score of 32 lands at #878 of 1,162 AI chart posts and #48 of 59 @EpochAIResearch posts."},{"factor":"form","text":"At 3.1K views against a 44.4K median for benchmark bar charts, the ratio is 0.07x."}],"verdict":"It sits in the Small but loved quadrant, at #878 of 1,162 AI chart posts.","news":{"headline":"@EpochAIResearch posts FrontierMath accuracy comparison of Grok models","dek":"The benchmark bar chart drew 3.1K views and a 1.20% engagement rate, above the 0.73% median among AI chart posts.","what":"@EpochAIResearch posted a FrontierMath accuracy comparison of Grok models on April 11, 2025. It was one of 3 posts from the account that day, alongside a GPQA Diamond accuracy comparison and an OTIS Mock AIME accuracy comparison.","numbers":"It reached 3.1K views, ranking #1,034 of 1,162 AI chart posts. Its score of 32 ranks #878 of 1,162 AI chart posts and #48 of 59 @EpochAIResearch posts.","lesson":"A benchmark bar chart at 3.1K views against a 44.4K median for the type still drew a 1.20% engagement rate against a 0.75% median for the type. The save rate was 0.097%.","implication":"At #48 of 59 @EpochAIResearch posts, this chart sits below the account's own 1.37% median engagement rate despite its 1.20% rate clearing the 0.73% median among AI chart posts."}},"zh":{"why":[{"factor":"engagement","text":"互动率1.20%，高于AI图表帖中位数0.73%，排第83百分位。"},{"factor":"rank","text":"综合得分32，在1162条AI图表帖中排第878，低于中位水平。"},{"factor":"form","text":"浏览量3086，仅为同类基准条形图中位数4.4万的0.07倍。"}],"verdict":"范围小但受欢迎，综合得分在1162条AI图表帖中排第878。","news":{"headline":"@EpochAIResearch发布Grok模型FrontierMath对比图","dek":"浏览量低但互动率高于中位数，收藏率仅0.097%。","what":"2025年4月11日，@EpochAIResearch发布1张基准条形图，对比Grok-3和Grok-3 mini的FrontierMath准确率。同日该账号另有2条帖子，分别关于GPQA Diamond和OTIS Mock AIME。","numbers":"浏览量3086，在1162条AI图表帖中排第1034，低于中位数4万。互动率1.20%，排第199。","lesson":"基准条形图互动率1.20%，高于同类中位数0.75%，但浏览量仅为同类中位数的0.07倍：高互动未带来高覆盖。","implication":"该帖在@EpochAIResearch的59条帖子中排第48，低于账号自身互动率中位数1.37%。浏览量低但互动率高于AI图表帖中位数，属于窄众高互动。"}},"lane":"en:amd/DeepSeek-V4.1-Flash zh:amd/DeepSeek-V4-Flash","checkedAt":"2026-10-13T20:16:14.899Z"}}