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.
More from Models
- Early User: Luna's Extra-High Reasoning Feels Free, Builds Lossless DLSS5 Driver — MickeySteamboat · 2026-09-30
- Sol 6.1 Extra High Finishes Daily Work Tasks for Just 1% of Usage, User Impressed — jdjohnson · 2026-09-30
- Model pickers are going away: all models will eventually hide behind a harness — HanchungLee · 2026-09-30
- GPT-6.1 Sol builds 3D keyboard assembly videos at 1/30th the price of Sonnet 5.5 — BorisMPower · 2026-09-30
- Claude Sonnet 5.5 coming to LMArena for limited-time testing — arena · 2026-09-30
- ARC Prize to Evaluate DeepSeek V4.1 Flash After Predecessor Hit 61.4% on ARC-AGI-2 — teortaxesTex · 2026-09-30