Thinky open-sources variable-loop model: more looping passes boost long-context but not knowledge benchmarks

simonguozirui · x · 2026-11-21

Thinky Machines released TML-d24-varloop-research, a variable-loop companion to Inkling 2 Mini (Loopling). Experiments show long-context benchmarks (GraphWalks BFS, MRCR v2) improve with more looping passes, while knowledge-intensive benchmarks (AA-Omniscience, SimpleQA Verified, SimpleVQA, WorldVQA) don't. Inkling 2 Mini outperforms July's Inkling 1.0 at just 2.7% of its size.

Related event: Team open-sources variable-looping model to test looping's effect on CoT monitorability(3 posts)→

Original post →

More from Models

Models channel →