Sol 5.6 Wins Word Puzzle Showdown
josh_bickett · x · 2026-07-15
Someone tested Sol 5.6 and Fable 5 using the same tricky word puzzle. The result: Sol 5.6 performed significantly better, with the author claiming it guessed 31 out of 32 target words almost perfectly. Fable 5, on the other hand, seemingly completely crashed after switching to Opus.
More from Models
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- OpenAI’s Codex + GPT-5.6 Sol hits 99% recall in Project APE verification tests — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Macaron V1 adds LoRA RL on GLM 5.2 and claims SOTA benchmark gains — Xianbao_QIAN · 2026-07-22
- OpenAI rolls out voice in GPT-Live, but the UI obscures search and reasoning — Graham_dePenros · 2026-07-22
- Moonshot’s Kimi K3 sets a new open-weights ECI record at 156 — scaling01 · 2026-07-22