GPT 6 Astra (high) ties WeirdML’s top score at 92.9%, a user reports
The user reports new individual high scores on 6 of 17 tasks and significantly less code than Sol and other recent GPT models, though still more than Claude.
TLDR
A user reports that GPT 6 Astra (high) scored 92.9% on WeirdML, matching Fable 5.1 (max) for the top score. They say Astra set new individual high scores on 6 of 17 tasks and wrote significantly less code than Sol and other recent GPT models, but more than Claude. On September 5, the user said a more careful analysis would follow once the max and pro max runs were done.
Combined views
25K
1 Source, first seen 25d ago