gpt-6POST
Critic questions fairness of GPT-6 Astra vs Sonnet 5.5 comparison
A commenter argues that comparing Sonnet 5.5 at low reasoning effort with GPT-6 Astra at higher reasoning effort is invalid, and that Opus 5.5 should be tested against GPT-6 Astra at the same reasoning levels.
Drogobo
@Dr0g0b0Archived 2026.09.30Originally posted 2026.09.30
Drogobo @Dr0g0b0Originally posted 2026.09.30
@katiserie literally sonnet 5.5 probably on low reasoning effort is not comparable to gpt 6 astra on a higher reasoning effort should've tested opus 5.5 against gpt 6 astra at same reasoning levels to really test it
x.com/dr0g0b0/status/2105030395658227884Archived 2026.09.30 10:24