Chetaslua
@chetaslua
AI researcher & reporter | I test new models on launch day, build working demos, and post prompts + results | Code:
加入 December 2024
184 正在关注 36.3K 粉丝
i gave Apodex 1.1 a messy synthetic benchmark, then changed the workload mid-run.
same tasks. different mix. the apparent leader flips.
the useful part: an interactive audit, cleaned data, and code to check the answer.
sponsored demo · @Apodex_AI
Try apodex：
显示更多
