Show HN: AI Vision Index, private tests of how well 36 AI models see
I wanted to know for my work which model is best at vision tasks (using both llms like claude and smaller models like YOLO - smaller specialist models are still not finished testing). I found that none of the public benchmarks were reliable: datasets were available (so they could have been used for training), and not precise enough tests. So we built our own tests, with a mix of rendered images, ai generated images, photos and videos. Every question & image pair has a specific answer, and we
阅读原始来源
来源记录
指标快照
points · 1 votes
2026-11-10 13:00:31.075Z
cumulative since publication
研究分析
变化记录
来源描述：I wanted to know for my work which model is best at vision tasks (using both llms like claude and smaller models like YOLO - smaller specialist models are still not finished testing). I found that none of the public benchmarks were reliable: datasets were available (so they could have been used for training), and not precise enough tests. So we built our own tests, with a mix of rendered images, ai generated images, photos and videos. Every question & image pair has a specific answer, and we
版本与成本证据
来源票数: 1 votes (2026年11月10日 UTC; cumulative since publication) 可供比较的近期同类记录：“Show HN: Deep Cuts – music discovery via credits instead of algorithms” (Show HN, 2026年11月10日)；“[分享创造] 自己攒了个 AI 说唱站，从 topic 到词、歌、视频都能走” (V2EX, 2026年11月10日)。主题相近仅用于导航，未核验其是否属于同一需求或独立证据。
适用与受影响对象
先明确变化影响的现有工作流，再判断是否升级。发布热度不证明效果提升；接口、价格或可用性变化也可能增加迁移工作。
缺失的比较信息
待补齐：新旧行为、受影响套餐与地区、生效时间、兼容性、回退路径及同一工作量下的成本。
采用与迁移验证
保存发布或政策原文，对新旧方案运行同一个任务并比较结果与完整账单；若涉及停服，先核验截止时间再安排迁移。