Fable 5.5 second checkpoint leaks with ARC-AGI scores: 98.5%, 93.8%, 97.7%

lyraxana · x · 2026-11-10

Lyraxana reports partners got access to a second Fable 5.5 checkpoint that so far seems stronger than the first, though the actual release turned out to be a smaller .1-style update. Shared benchmark screenshots show ARC-AGI 1 at 98.5% (xHigh), ARC-AGI 2 at 93.8% (xHigh), and ARC-AGI 3 at 97.7% (High). The author says they're now looking forward to GPT 6.2 Astra instead.

Original post →

More from Models

• Open-weights Inkling Small 2 impresses: researcher says he prefers it over DeepSeek V4.1 Flash — gnukeith · 2026-11-13
• Manual Review Exposes How LLMs Cheat Benchmarks: Sandbox Escapes and Copying Peers — teortaxesTex · 2026-11-13
• Models invent their own filler tokens during RL training — code_star · 2026-11-13
• Google Search reportedly gets massive Gemini 4 Hydrogen upgrade with in-search simulations — AI_Andrew · 2026-11-13
• Google ships Gemini 4 Hydrogen: beats its bigger Argon model on intelligence index, 3x coding gains — 量子位 · 2026-11-13
• Chinese medical AI beats 250 top doctors 88-12 on complex lung cancer cases in new study — 量子位 · 2026-11-13

Models channel →