MNIST-PRO Benchmark
Explore score history ↗Evaluates agents' perceptual state construction in partially observable environments through a sequential glimpse-based MNIST digit search with lookback constraints, scored on recognition accuracy across memory representations.
- Released
- 2026-08-31
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
MNIST-PRO paper
No reported scores are on record for this benchmark yet.