從預訓練模型到建置服務引擎,AI 助理能不能完成整套工作?
- 卡內基美隆大學的新論文用 Singularity-Bench 測試 6 種端到端任務,並在相同 GPU 上拿成果和 SGLang 等生產工具比較。Opus 5.5 的 Singularity-Index 是 1.25,人類基準為 1。
- 另外 10 個 AI 助理平均是 0.58。它建置的服務引擎每 GPU 小時賺取 11.52 USD,SGLang 則是 8.18 USD。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
這項基準把 AI 助理完成訓練、推論與叢集管理工作的成果,和同 GPU 上的生產工具比較,可瞭解它們在端到端工程任務上的表現。
New Carnegie Mellon paper finds that Opus 5.5 + Claude Code built a pre-training pipeline, an inference engine, and a cluster orchestrator that matched or beat production tools like SGLang and NVIDIA Dynamo on the same GPUs.
Singularity-Bench gives agents 6 end-to-end jobs, from pre-training a model to building a serving engine. Each result is scored against a production system, such as SGLang or Claude Code, on the same GPUs.
Opus 5.5 scored a Singularity-Index of 1.25, where 1 equals the human baselines, while the other 10 agents averaged 0.58. Its serving engine earned 11.52 USD per GPU-hour against 8.18 for SGLang.