GPT-6.1 Sol beats 2x-cost models on ClickUp's knowledge-work benchmark

mathemagic1an · x · 2026-09-30

ClickUp's mathemagic1an reports that OpenAI's new GPT-6.1 Sol is exceptionally strong at complex knowledge-work tasks. On ClickUp Bench, their internal eval for white-collar knowledge work, the model expands the Pareto frontier, outperforming models that cost twice as much. GPT-6.1 Sol is now live in ClickUp.

Original post →

More from Models

Models channel →