EnigmaEval is a private benchmark of 1,184 puzzle-hunt problems on which state-of-the-art vision-language models score 7.0% on normal and 0% on hard items.
Grandmaster Puzzles
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
EnigmaEval: A Benchmark of Long Multimodal Reasoning Challenges
EnigmaEval is a private benchmark of 1,184 puzzle-hunt problems on which state-of-the-art vision-language models score 7.0% on normal and 0% on hard items.