StateSight - Cube Net Folding: leaderboard
Metric: Accuracy (%; naming the face opposite a highlighted face after folding a cube net; 300 procedurally generated single-image prompts with deterministic oracle labels, exact-match, answer-only prompt). Source: arxiv.org. Saturation forecast: Around December 2026. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (Non-reasoning) | 59.3 |
Interactive version: theaggregate.ai/benchmark?slug=statesight-cube-net-folding · How It Works · Data refreshed daily, snapshot 2026-09-26.