Benchmark RadarAI BENCHMARK PROFILE
RotOutBench
Paired diagnostic benchmark for rotated-outcome prediction in vision-language models, spanning open visual cases and controlled text-image rotations, with accuracy metrics for direct reading and prediction.
- Released
- 2026-06-01
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Evaluates a specific cognitive ability in VLMs, but lacks a standalone public comparison path.
Motivation
Can vision-language models predict what a 180{\deg} rotation would reveal from the original image alone?
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.