Inkling 2 Mini gains +61.5 from Parallel Search, far outpacing Fable 5.2's +29.5
simonguozirui · x · 2026-11-22
A widely shared thread highlights Thinky Machines' Inkling 2 Mini, which shows an unusual +61.5 lift with Parallel Search versus just +29.5 for Fable 5.2. Observers describe it as a model of nearly pure "intelligence" with little world knowledge, suggesting strong potential for domain-specific applications.
Related event: Inkling 2 Mini Tops Cost-Performance Rankings as 26B Open-Weight Model(2 posts)→
More from Models
- Gemini 4 Neon Matches Top Models but Costs ~30 Cents Per Task, Same as Fable 5.2 — ChrisGPT · 2026-11-22
- AIs often refuse open math problems, citing low odds of success — Jsevillamol · 2026-11-22
- Mathematician pushes back on Anthropic RH proof skepticism: using everything is a good sign — harris_edouard · 2026-11-22
- OpenAI engineer confirms GPT-Live cache affinity bug, fix rolling out Monday — pbbakkum · 2026-11-22
- Claude Code caps Kimi K3.1 at 200K: 148 compactions across 95 trials vs Opus's 797K — zainhas · 2026-11-22
- Early Gemini Neon blind tests: excessive thinking tokens and speed are the top failure point — bindureddy · 2026-11-22