OpenAI’s cost and performance on a bug-hunting evaluation
The post also describes V4.1 as catching up, but says it still falls short of Grok’s level.
TLDR
One user praises OpenAI’s showing on a bug-hunting evaluation, calling it “cheaper and better than anyone.” The same post says V4.1 is catching up, though “not even Grok tier.”
Combined views
54.9K
2 Sources, first seen ago