Claude edges ChatGPT and Gemini in 1000-character story test
A user conducted a creative writing experiment asking ChatGPT, Claude, and Gemini to write a complete short story within 1000 characters. The prompt required the AI to choose its own genre and theme, avoid safe choices, and allow for two rounds of revision. The goal was to produce a coherent work that leaves a lasting impression on the reader.
Key points
- Claude won the story contest with 263.70 points, narrowly beating ChatGPT and Gemini.
- Gemini and Claude exceeded the 1000-character limit, incurring score deductions.
- ChatGPT’s story was only 695 characters, leaving significant unused space.
All three models struggled with the strict character limit. Gemini’s story, "Beyond the Frequency," came in at 1117 characters, while Claude’s, "Forgotten Items," reached 1069 characters. ChatGPT’s entry, "The Last Customer," was significantly shorter at 695 characters. The author applied deductions for the overages, reducing Gemini’s score by 11.7% and Claude’s by 6.9%.
Scoring was performed by the three AI models themselves and the user, converted to an 80-point scale. Claude took first place with a total of 263.70 points, narrowly beating ChatGPT (262.60 points) and Gemini (238.26 points). The user noted that each model displayed distinct stylistic traits: Gemini focused on world-building, Claude on emotional compression, and ChatGPT on negative space. The test highlighted the difficulty of adhering to precise length constraints in generative AI.
AI Short Story Showdown! — What Will ChatGPT, Claude, and Gemini Write in 1000 Characters?
note.com · 23 September 2026
Loading the full article…
This text was published by note.com and written by Admin-00. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Anthropic launches Claude Opus 5.5, claims 40% lower running costs than Opus 5 · 31 src
- Xiaomi releases MiMo-V2.6-Pro-RL, a 1.02T/42B open omnimodal model trained via scaled RL · 6 src
- OpenAI and Anthropic release new AI models with 40-50% price cuts · 36 src
- Anthropic has a 71% chance of leading AI model market by end of 2026 · 1 src
- Google releases Gemini 3.8 Flash TTS and Flash-Lite TTS with voice cloning and 100+ languages · 8 src
Comments
via GitHub Discussions