News for hackers. Stuff that matters.

A comment on Huawei releases an open weight model trained on Huawei Ascend GPUs. Parent comment

Re:Huawei releases an open weight model trained on Huawei As... by conradev on Wednesday July 02, 2025 @11:53AM (#44445258)
It’s good at a lot of things:

  GPT‑4.1 scores 54.6% on SWE-bench Verified, improving by 21.4%abs over GPT‑4o and 26.6%abs over GPT‑4.5—making it a leading model for coding.
https://openai.com/index/gpt-4-1/
[ Parent | on HN ]
Re:Huawei releases an open weight model trained on Huawei As... by coliveira on Wednesday July 02, 2025 @06:27PM (#44449502)
They are trained on these "benchmarks", that's why they score better.
[ Parent | on HN ]
Re:Huawei releases an open weight model trained on Huawei As... by elzbardico on Wednesday July 02, 2025 @07:02PM (#44449736)
If they were trained on those benchmarks they would score 100%
[ Parent | on HN ]
Re:Huawei releases an open weight model trained on Huawei As... by coliveira on Wednesday July 02, 2025 @07:15PM (#44449837)
They show how bad they are, they cannot score 100% on benchmarks they were trained on.
[ Parent | on HN ]