Epoch AI's Furniture Assembly Benchmark Shows Big Spatial Reasoning Gains

Epoch AI released the Furniture Assembly Benchmark, where models identify assembly errors from manuals and photos; scores jumped from 28% to 80% in just 10 months.

2026-09-24 ~ 2026-09-25 · 2 related posts

• IKEA Assembly Benchmark: Top Model Score Jumped From 28% to 80% in 10 Months — emollick · 2026-09-24
• Epoch AI's Furniture Assembly Benchmark: top model score jumped from 28% to 80% in 10 months — rohanpaul_ai · 2026-09-25