← All models

GPT 5.5 editing test

OpenAI · Tested Oct 28, 2026 · 1m 50s · $0.94

75/90 caught

  • Grammar & spelling40/45
  • Repetitions10/15
  • Redundancy11/15
  • Consistency14/15

99 comments · 6 extra flags

GPT 5.5 caught 75 of 90 planted mistakes, tied 8th of 16 models tested. It was strongest on contradictions (14 of 15) and missed most on repeated words (10 of 15). The 4 checks took 1m 50s and cost $0.94; asked for all of them in one prompt, it caught 67.

Every comment GPT 5.5 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 · 15