{"id":"3f1639f8a8d8","page":"/c/3f1639f8a8d8/","topic":"GPQA Diamond accuracy comparison of AI models","publisher":"@EpochAIResearch","official":false,"platform":"X","publishedAt":"2025-04-18T23:49:52.000Z","model":"Gemini 2","form":"benchmark-bars","metrics":{"views":8785,"likes":83,"reposts":3,"quotes":1,"replies":1,"saves":7},"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":755,"of":1162},"company":{"n":27,"of":59}},"views":{"industry":{"n":840,"of":1162},"company":{"n":23,"of":59}},"likes":{"industry":{"n":786,"of":1162},"company":{"n":25,"of":59}},"eng":{"industry":{"n":310,"of":1162},"company":{"n":41,"of":59}},"save":{"industry":{"n":565,"of":1162},"company":{"n":47,"of":59}}},"percentiles":{"industry":{"views":0.2775387263339071,"likes":0.3244406196213425,"eng":0.7336488812392427,"save":0.5141996557659209},"company":{"views":0.6186440677966102,"likes":0.5847457627118644,"eng":0.3135593220338983,"save":0.211864406779661}},"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":1.6644562334217508,"vsCompanyLikes":1.3174603174603174,"viewsPerFollower":null,"viewsPerDay":16.211389289054836},"followers":null,"reads":[{"at":"2026-10-12T15:49:44.625Z","views":8785,"likes":83,"reposts":3,"quotes":1,"replies":1,"saves":7,"source":"x-search-cache"}],"chartData":"/api/charts/3f1639f8a8d8.json","copy":{"en":{"why":[{"factor":"engagement","text":"Its 1.00% engagement rate sits above the 0.73% median for all AI chart posts, ranking #310 of 1,162."},{"factor":"launch-day","text":"On launch day, this post ranked #3 of 4 by views among the account's posts that day."},{"factor":"rank","text":"Its score of 40 ranks #755 of 1,162 AI chart posts, below the median."}],"verdict":"Small but loved: views below the AI chart median, engagement at or above it, score rank #755.","news":{"headline":"@EpochAIResearch GPQA Diamond accuracy chart draws modest views","dek":"A benchmark bar chart comparing 8 AI models on GPQA Diamond accuracy, posted April 18, 2025.","what":"On April 18, 2025, @EpochAIResearch posted a benchmark bar chart comparing GPQA Diamond accuracy for 8 models. It was one of 4 posts that day, alongside charts on FrontierMath, MATH Level 5, and OTIS Mock AIME.","numbers":"The post drew 8.8K views, ranking #840 of 1,162 AI chart posts, below the 39.9K median. Its engagement rate was 1.00%, ranking #310 of 1,162.","lesson":"With 8 models shown in a single chart, the post's save rate was 0.080%, below the account's median engagement of 1.37%. A clean table of many models may not drive saves.","implication":"This post's score of 40 ranks #27 of 59 for @EpochAIResearch, below the account's median engagement rate of 1.37%. It shows that even with above-median engagement, low views cap overall performance."}},"zh":{"why":[{"factor":"engagement","text":"互动率1.00%，高于AI图表帖中位数0.73%，排第73百分位。"},{"factor":"launch-day","text":"发布当天有4条帖子，本条浏览量在4条中排第3。"},{"factor":"rank","text":"综合得分40，在1162条AI图表帖中排第755，低于中位水平。"}],"verdict":"范围小但很受欢迎，综合得分在1162条AI图表帖中排第755。","news":{"headline":"@EpochAIResearch发布GPQA Diamond对比图","dek":"浏览量8785，互动率1.00%，高于中位数。","what":"2025年4月18日，@EpochAIResearch发布1张基准柱状图，对比8个模型的GPQA Diamond准确率。当天该账号还有3条其他帖子。","numbers":"浏览量8785，在1162条AI图表帖中排第840，低于中位数4万。互动率1.00%，排第310。","lesson":"互动率1.00%高于中位数0.73%，但浏览量低于中位数，说明高互动未带来高覆盖。","implication":"在@EpochAIResearch的59条帖子中排第27，互动率低于该账号中位数1.37%，表现中等。"}},"lane":"amd/DeepSeek-V4-Flash","checkedAt":"2026-10-13T20:15:17.711Z"}}