GPT-5.6 Sol Pro edges Fable in a Churchill-insult prompt test
emollick · x · 2026-07-23
The author compared several models on a prompt to invent a fake but believable, witty Churchill-style insult and explain the context.
- GPT-5.6 Sol Pro was judged the best, though “none are amazing.”
- Fable was also competitive and could plausibly take first.
- Kimi and Gemini were said to miss the mark badly.
Related event: Wharton Professor Tests LLMs on Churchill-Style Insults(2 posts)→
More from Models
- User hits ChatGPT Pro’s $200 cap and says fallback mode is too opaque — Sauers_ · 2026-07-23
- Bigger models and longer thinking time expand the space of good decisions — gabriel1 · 2026-07-23
- DecBench tracks how close LLMs are to near-perfect binary decompilation — moyix · 2026-07-23
- Local open-source agent says it beats Hermes 37 to 31 on GAIA Level 1 — kimmonismus · 2026-07-23
- Anthropic says a cutoff-date bug showed March 2026 in some domains — _arohan_ · 2026-07-23
- A simple quant benchmark could expose frontier-model failures fast — PtrPomorski · 2026-07-23