The authors introduce PARROT-360V, a benchmark of 2,487 visual word puzzles on which three leading VLMs score 28-56%, much lower than on common benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Visual Understanding: Introducing PARROT-360V for Vision Language Model Benchmarking
The authors introduce PARROT-360V, a benchmark of 2,487 visual word puzzles on which three leading VLMs score 28-56%, much lower than on common benchmarks.