Benchscope
Benchmark any LLM endpoint for your workload
什么是 Benchscope？
Compare provider-hosted LLM endpoints, or run the same benchmarks against your own OpenAI-compatible endpoint URL. Inspect quality, latency, prompts, raw outputs, and methodology before choosing a model for inference.
截图
?
还没有评论，来抢沙发吧！
X 上关于 Benchscope 的真实讨论
去 X 发帖