{"id":"fe3b8adbb805","page":"/c/fe3b8adbb805/","topic":"GPT-5 vs Claude on SWE-bench Verified","publisher":"@EpochAIResearch","official":false,"platform":"X","publishedAt":"2025-08-12T23:30:10.000Z","model":"GPT-5","form":"benchmark-bars","metrics":{"views":4698,"likes":61,"reposts":5,"quotes":2,"replies":3,"saves":3},"readAt":"2026-10-12T21:30:08.589Z","chartsInPost":1,"score":36,"scoreWeights":{"views":0.4,"likes":0.3,"eng":0.15,"save":0.15},"quadrant":"loved","ranks":{"score":{"industry":{"n":814,"of":1162},"company":{"n":39,"of":59}},"views":{"industry":{"n":961,"of":1162},"company":{"n":34,"of":59}},"likes":{"industry":{"n":833,"of":1162},"company":{"n":31,"of":59}},"eng":{"industry":{"n":88,"of":1162},"company":{"n":24,"of":59}},"save":{"industry":{"n":679,"of":1162},"company":{"n":49,"of":59}}},"percentiles":{"industry":{"views":0.173407917383821,"likes":0.28528399311531843,"eng":0.9246987951807228,"save":0.41609294320137696},"company":{"views":0.4322033898305085,"likes":0.4830508474576271,"eng":0.6016949152542372,"save":0.17796610169491525}},"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":0.8901098901098901,"vsCompanyLikes":0.9682539682539683,"viewsPerFollower":null,"viewsPerDay":11.030327169171928},"followers":null,"reads":[{"at":"2026-10-12T15:34:33.759Z","views":4698,"likes":61,"reposts":5,"quotes":2,"replies":3,"saves":3,"source":"x-search-cache"},{"at":"2026-10-12T15:49:44.625Z","views":4698,"likes":61,"reposts":5,"quotes":2,"replies":3,"saves":3,"source":"x-search-cache"}],"chartData":"/api/charts/fe3b8adbb805.json","copy":{"en":{"why":[{"factor":"engagement","text":"Its 1.51% engagement rate sits at the 92nd percentile among AI chart posts, 2.1x the 0.73% median."},{"factor":"launch-day","text":"The post landed #2 of 2 by views among this account's posts that day."},{"factor":"rank","text":"Its score of 36 places it #814 of 1,162 AI chart posts and #39 of 59 @EpochAIResearch posts."}],"verdict":"The post sits in the Small but loved quadrant, at #814 of 1,162 AI chart posts.","news":{"headline":"@EpochAIResearch charts GPT-5 vs Claude on SWE-bench Verified","dek":"A benchmark bar chart of GPT-5 against Claude models drew 4.7K views and a 1.51% engagement rate.","what":"@EpochAIResearch posted a benchmark bar chart on August 12, 2025, comparing GPT-5 and Claude models on SWE-bench Verified. The same day the account posted 1 other chart, on GPT-5 performance on GPQA Diamond.","numbers":"The post reached 4.7K views, ranking #961 of 1,162 AI chart posts, against a median of 39.9K views among AI chart posts. Its score of 36 ranks #814 of 1,162 AI chart posts and #39 of 59 @EpochAIResearch posts.","lesson":"The chart shows printed values from 35% to 63% across 6 models, and the post's  aper engagement rate of 1.51% sits at the 92nd percentile among AI chart posts. A 6-model benchmark bar chart drew 4.7K views, below the 39.9K median among AI chart posts.","implication":"At #39 of 59 @EpochAIResearch posts, this chart post trails the account's own output while its 1.51% engagement rate runs above the 1.37% median for this account. The 4.7K views against the 39.9K median among AI chart posts leave the reach gap wide."}},"zh":{"why":[{"factor":"engagement","text":"互动率1.51%，是AI图表帖中位数0.73%的2.1倍，排第88位。"},{"factor":"launch-day","text":"发布当天在@EpochAIResearch的2条帖子中浏览量排第2，低于同日另一条。"},{"factor":"rank","text":"综合得分36，在1162条AI图表帖中排第814，在自家59条中排第39。"}],"verdict":"范围小但很受欢迎，综合得分在1162条AI图表帖中排第814。","news":{"headline":"@EpochAIResearch发GPT-5对比Claude的SWE-bench图表","dek":"浏览量低但互动率高于中位数，排名靠后。","what":"2025年8月12日，@EpochAIResearch发布1张基准柱状图，对比GPT-5与Claude在SWE-bench Verified上的表现。同日该账号还有1条关于GPT-5在GPQA Diamond的帖子。","numbers":"浏览量4698，在1162条AI图表帖中排第961，低于中位数4万。互动率1.51%，排第88，是AI中位数0.73%的2.1倍。","lesson":"互动率1.51%排第92百分位，但浏览量仅4698，低于中位数4万，范围小但受欢迎。","implication":"该帖在@EpochAIResearch的59条帖子中排第39，互动率高于自家中位数1.37%，但浏览量排名靠后，说明高互动未带来高曝光。"}},"lane":"en:amd/DeepSeek-V4.1-Flash zh:amd/DeepSeek-V4-Flash","checkedAt":"2026-10-13T21:08:54.109Z"}}