{"id":"2a72683364a0","page":"/c/2a72683364a0/","topic":"GPQA Diamond accuracy for Claude models","publisher":"@EpochAIResearch","official":false,"platform":"X","publishedAt":"2025-05-28T19:46:05.000Z","model":"Claude Opus 4","form":"benchmark-bars","metrics":{"views":3336,"likes":30,"reposts":1,"quotes":1,"replies":1,"saves":1},"readAt":"2026-10-12T21:30:08.589Z","chartsInPost":1,"score":23,"scoreWeights":{"views":0.4,"likes":0.3,"eng":0.15,"save":0.15},"quadrant":"loved","ranks":{"score":{"industry":{"n":1032,"of":1162},"company":{"n":55,"of":59}},"views":{"industry":{"n":1018,"of":1162},"company":{"n":37,"of":59}},"likes":{"industry":{"n":959,"of":1162},"company":{"n":47,"of":59}},"eng":{"industry":{"n":320,"of":1162},"company":{"n":43,"of":59}},"save":{"industry":{"n":992,"of":1162},"company":{"n":55,"of":59}}},"percentiles":{"industry":{"views":0.12435456110154905,"likes":0.17771084337349397,"eng":0.7250430292598967,"save":0.14672977624784853},"company":{"views":0.3813559322033898,"likes":0.2033898305084746,"eng":0.2796610169491525,"save":0.07627118644067797}},"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":0.6320575975748389,"vsCompanyLikes":0.47619047619047616,"viewsPerFollower":null,"viewsPerDay":6.6444618450068615},"followers":null,"reads":[{"at":"2026-10-12T15:35:27.549Z","views":3336,"likes":30,"reposts":1,"quotes":1,"replies":1,"saves":1,"source":"x-search-cache"}],"chartData":"/api/charts/2a72683364a0.json","copy":{"en":{"why":[{"factor":"rank","text":"Its score of 23 lands at #1,032 of 1,162 AI chart posts, below the field."},{"factor":"saves","text":"Saves came in at 0.030%, the 15th percentile among AI chart posts against a 0.076% median."},{"factor":"launch-day","text":"It was #2 of 4 posts from this account that day, level with the day's own output."}],"verdict":"It sits in Small but loved, at #1,032 of 1,162 AI chart posts.","news":{"headline":"@EpochAIResearch charts GPQA Diamond accuracy for Claude models","dek":"The post drew 3.3K views and a 0.99% engagement rate, with saves at 0.030%.","what":"@EpochAIResearch posted a benchmark bar chart on May 28, 2025 covering GPQA Diamond accuracy for Claude models. It was one of 4 posts from the account that day, alongside SWE-bench Verified and OTIS Mock AIME 2024-2025 charts.","numbers":"It reached 3.3K views, ranking #1,018 of 1,162 AI chart posts, against a median of 39.9K. Its score of 23 ranks #1,032 of 1,162 AI chart posts and #55 of 59 @EpochAIResearch posts.","lesson":"A save rate of 0.030%, the 15th percentile among AI chart posts, sits below the 0.076% median: this 7-model comparison gave readers little to bookmark. The 0.99% engagement rate sits at or above the AI chart median while views stay below it.","implication":"At #55 of 59 @EpochAIResearch posts, this chart trails the account's own output, and its 3.3K views sit far under the 39.9K median among AI chart posts. The 0.030% save rate, against a 0.076% median, marks a wide gap on the measure that keeps a chart citable."}},"zh":{"why":[{"factor":"rank","text":"综合得分23分，在1162条AI图表帖中排第1032，属于下游水平。"},{"factor":"saves","text":"收藏率0.030%，低于中位数0.076%，排第992位，互动偏弱。"},{"factor":"launch-day","text":"发布当天4条帖子中排第2，浏览量居中，无突出表现。"}],"verdict":"范围小但受欢迎，综合得分在1162条中排第1032。","news":{"headline":"@EpochAIResearch发GPQA Diamond图表","dek":"浏览量3336，互动率0.99%，收藏率仅0.030%。","what":"2025年5月28日，@EpochAIResearch发布GPQA Diamond准确率柱状图，展示Claude Sonnet 4和Opus 4的表现。当天另有3条帖子，包括SWE-bench和OTIS Mock AIME。","numbers":"浏览量3336，在1162条AI图表帖中排第1018，低于中位数4万。互动率0.99%，收藏率0.030%，排第992。","lesson":"收藏率0.030%，低于中位数0.076%，在1162条中排第992：低收藏率与低浏览量一致。","implication":"该帖在@EpochAIResearch的59条帖子中排第55，综合得分23，表现靠后。"}},"lane":"en:amd/DeepSeek-V4.1-Flash zh:amd/DeepSeek-V4-Flash","checkedAt":"2026-10-13T20:11:00.406Z"}}