Event ·Multi-source

XStack 基准发布:测试智能体能否把 PyTorch 仓库迁移到 JAX

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。

Current read

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。

11 sources62° AI heatLast updated 2026/11/5 18:55:54

Evidence

11 sources
Related source 2rohanpaul_ai
View source
Related source 3@atomic_chat_hq
View source
Related source 8Stanford AI Lab
View source
Related source 9techcrunch
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.