Same prompt head-to-head: Fable 5.2 spends 3x time, 2x cost for auteur flair
iamfakhrealam · x · 2026-11-11
Japanese user mukusns gave the identical one-paragraph prompt to the newly released Claude Fable 5.2 and Opus 5.5 for movie-trailer title sequences:
- Opus 5.5: delivered a polished, classic trailer in 2m40s — the craftsman
- Fable 5.2: invented its own visual concept of a red border line, blacked out credits and surfaced a hidden face in code — the director — at roughly 3x the time and 2x the cost
Author's takeaway: use Opus for daily work, Fable only for the core of a piece. Note: Pro-tier access to Fable 5.2 ends Nov 17, 16:59 JST.
More from Models
- Theory: Typos Disrupt LLM Tokenization, Which May Explain Why AI Text Has a Distinct Smell — menhguin · 2026-11-11
- LMArena co-founder explains AI evaluation methodology and policy in new podcast — MattPerault · 2026-11-11
- Runway open-sources Praxis-1, turning video pretraining into real robot control — runwayml · 2026-11-11
- DeepMind launches AlphaGenome 2, spotting nearly 2x more gene-regulating mutations — GoogleDeepMind · 2026-11-11
- MazeBench: Fable 5.2 scores 15%, near-frontier at half price; Gemini 4 Carbon 11% — patience_cave · 2026-11-11
- ERNIE 5.5 Flash Preview enters LMArena Battle Mode for crowdsourced ranking — arena · 2026-11-11