GoKawiilCNET Test Finds Gemini Outperforms ChatGPT on Visual Recognition Tasks
CNET ran a side-by-side comparison of ChatGPT and Gemini's ability to interpret images, including handwritten notes scribbled on an e-ink tablet using a passage from The Hound of the Baskervilles. In this test, ChatGPT struggled to correctly transcribe the messy handwriting, misreading key phrases and producing largely inaccurate output compared to what was actually written.
GoKawiil's interpretation of the reporting above, not reported fact.
As AI assistants increasingly rely on cameras and image uploads to interpret the physical world, accuracy in reading handwriting, objects and scenes becomes a practical differentiator between competing chatbots. Errors in basic visual tasks like transcription raise questions about reliability for real-world uses such as digitizing notes or assisting visually impaired users.
- ChatGPT inaccurately transcribed a handwritten passage in CNET's test.
- The comparison used identical photos and prompts for both chatbots to ensure fairness.
- Multimodal AI performance varies significantly between ChatGPT and Gemini despite both companies touting visual upgrades.
Boox Note Air4 C E-Ink Tablet — The handwriting test in this comparison started on an e-ink tablet, and the Boox Note Air4 C is a great one for scribbling notes you can later photograph or export for an AI to read. It pairs paper-like writing with Android apps, so you can jot ideas and send them straight into ChatGPT or Gemini.
See Boox Note Air4 C E-Ink Tablet on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: cnet.com — Blake Stimac, 2026-08-24
Published there as: “ChatGPT vs. Gemini: Which Chatbot Is Better at Seeing the World Around You?”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.