XStack 基准发布：测试智能体能否把 PyTorch 仓库迁移到 JAX
XStack: A Benchmark for ML Repo Migration
把 PyTorch 仓库自动改成 JAX 版的智能体测评，Claude Opus 5 通过 75%，其他模型差距挺大，做工程自动化的可以看看。
arXiv 论文 2611.08472 提出 XStack 基准，评估智能体将 PyTorch/NVIDIA GPU 仓库迁移为 JAX/TPU 仓库的能力。评分以源仓库已发表结果为标准，由作者认证和校准。成绩方面，Claude Opus 5 通过率 75%，GPT-5.6-sol 45%，其余智能体均不超过 40%。该基准覆盖整个仓库，属于长周期任务，旨在推动 ML 代码跨框架和硬件迁移的可靠性可度量。
XStack: A Benchmark for ML Repo Migration
ML code should run where researchers choose, not where it was first written. Today, machine learning code mainly lives in two ecosystems, PyTorch on NVIDIA GPUs and JAX on Google TPUs. Migrating repositories between them means building and testing across frameworks and hardware. This migration is (1) a practical need, since it unlocks different hardware for researchers, and (2) a natural benchmark: it involves different frameworks and hardware, covers whole repositories, and is long-horizon and challenging. We introduce XStack, a benchmark that evaluates agents on migrating ML repositories between these two ecosystems. Each agent receives a PyTorch repository and a clean TPU machine and must deliver a JAX repository. Its output passes if it meets our grading criteria, based on the source repository's published result, authenticated and calibrated by us. Migration by agents remains unreliable: Claude Opus 5 passes 75%, GPT-5.6-sol 45%, and every other agent at most 40%. XStack is a step toward freeing ML code from its ecosystem. We release XStack to make progress toward reliable migration across frameworks and hardware measurable.