The benchmark table is manipulative, borderline lying through statistics. In every line the top performing cell is marked red. Except the line where Sol leads, there it is marked in gray.
The benchmark table is manipulative, borderline lying through statistics. In every line the top performing cell is marked red. Except the line where Sol leads, there it is marked in gray.
I think that’s indicating that it’s only slightly higher.
I would be very surprised if the only row where OpenAI leads was coincidentally colored differently. I'm sure they have an official reasoning for it. But this communication is dishonest.