Princeton Reportedly Introduces SSoN Spatial Intelligence Benchmark
AI summary
DoNews reports that Princeton University introduced SSoN, a benchmark for evaluating spatial intelligence in large models. The cited results show 83.3% accuracy for humans, while the highest accuracy reported among large models was 39.7%.
In-depth insight
The reported performance gap highlights spatial reasoning as a measurable area where large models lag human accuracy.
The source text is unavailable here. Read the original for the full story.