Optima 上线：用自有数据构建定制 AI 基准测试
Optima tackles AI benchmarking's biggest flaw by letting users test models against their own data
Artificial Analysis has launched Optima, a platform that lets users build custom AI benchmarks from their own data and workflows. Models can be compared not just on quality but also on cost and time per task. For agent-based applications, those metrics often tell you more than raw token pricing.
Artificial Analysis 推出了 Optima，这是一个让用户能够基于自己的数据和工作流程构建定制 AI 基准测试的平台。模型不仅可以在质量上进行比较，还可以在每项任务的成本和耗时上进行比较。对于基于代理的应用，这些指标往往比原始 token 定价更能说明问题。
The article Optima tackles AI benchmarking's biggest flaw by letting users test models against their own data appeared first on The Decoder.
文章《Optima 通过让用户用自己的数据测试模型，解决了 AI 基准测试的最大缺陷》最初出现在 The Decoder 上。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力