1
Qwen team confirms data quality issues in GPQA and HLE
A paper reveals significant errors in the test sets, corroborating findings from the DeepSeek-Overclock project.
0 comments
No comments yet. Be the first to share your thoughts!
A paper reveals significant errors in the test sets, corroborating findings from the DeepSeek-Overclock project.
No comments yet. Be the first to share your thoughts!