← All models

GPT-6.1 Sol editing test

OpenAI · Tested Oct 27, 2026 · 1m 4s · $0.20

87/90 caught

  • Grammar & spelling43/45
  • Repetitions14/15
  • Redundancy15/15
  • Consistency15/15

99 comments · 4 extra flags

GPT-6.1 Sol caught 87 of 90 planted mistakes, 2nd of 16 models tested. It was strongest on redundancies (15 of 15) and missed most on repeated words (14 of 15). The 4 checks took 1m 4s and cost $0.20; asked for all of them in one prompt, it caught 80.

Every comment GPT-6.1 Sol left on our 6,000-word test story, where it left it. Click a missed mistake to find it in the text. The checks come from icanwrite, a markdown editor for writers.

Missed · 3