X · @emollick
· X / Twitter
The metrics discussion at OpenAI is a little confusing to me. I appreciate the clarification about bad benchmarks, but they spent a lot of money devel…
The metrics discussion at OpenAI is a little confusing to me. I appreciate the clarification about bad benchmarks, but they spent a lot of money developing a very good benchmark of autonomous model ability at hard tasks, GDPval, and haven't reported it for GPT-5.6.OpenAI: We audited SWE-Bench Pro, one of the most widel