产品

Artificial Analysis 更新 Optima,支持自定义模型基准测试

精选理由

Artificial Analysis 的 Optima 更新了,现在能用你自己的任务建基准,从智能、成本、速度三个维度对比各家模型。

Artificial Analysis 更新了 Optima 平台,用户可在 3 步内创建针对自身用例的个性化基准测试。新版本支持在最新模型上运行自定义任务,并从智能水平、成本、速度三个维度进行对比。Optima 定位为让用户用自己的评测任务评估模型,而非依赖通用基准。

原文 · Artificial Analysis

With our latest update, it is now easier than ever to create and run custom benchmarks in Optima. This allows you to evaluate models on evals tailored to your use cases

With Optima you can:

➤ Go from idea to personalized benchmark in 3 steps

➤ Compare model intelligence, cost and speed for your use case

➤ Run your own tasks on the latest models