Skip to content
Models

GPT-6.1 Sol nearly matches the no-CoT performance of GPT-6 Astra.

Summary I ran GPT-6 Sol and GPT-6.1 Sol on the task suite from Think Fast . Surprisingly, 6.1 Sol performs substantially better than 6 Sol, almost matching the performance of GPT-6 Astra. The plot below gives a quick overview of the results: Measured by mean a

LessWrongAnalysis or commentary·