Creative writing model bake-off: author prefers Muse Spark, says GPT-6 can't write paragraphs
sam_paech · x · 2026-09-07
Blogger sampaech ran a subjective creative-writing bake-off across GPT-6-Astra, Fable 5.1, Muse Spark 1.3, and Gemini 3.8 Flash.
His takeaways:
- Muse Spark 1.3 is his favorite: it simply does what you ask without imposing an obnoxious house style.
- Fable 5.1 has converged on its own flavor of "claudeslop" and can no longer write normally.
- GPT-6-Astra has "forgotten how to write in paragraphs."
He half-jokingly suggests reviving the old tradition of reading model rollouts with your own eyeballs instead of relying on benchmark scores.
Related event: New Creative Writing Benchmarks: Muse Spark Praised, GPT-6 Criticized(4 posts)→
More from Models
- LLM-judged writing evals are blind to readability issues from reward model optimization — koltregaskes · 2026-09-07
- Doctor runs Astra on Radiology's Last Exam, says he's 'getting first glimpse of AGI' — DrDatta_AIIMS · 2026-09-07
- Astra 6 Plus users burn 1,000 credits on one prompt, suspect forced upsell to Pro — YourBlanket · 2026-09-07
- GPT-6 Astra vs. Claude Fable-5.1: a hands-on guide to this week's flagship releases — rubenhassid · 2026-09-07
- OpenRouter and US Are Major Fraud Targets, Says Dev as Stripe Steps Into LLM Risk Control — jeff_weinstein · 2026-09-07
- The leaderboard fight on LMArena is heating up again — jonathan_wilke · 2026-09-07