A new Chinese K-12 multimodal benchmark with 33,660 questions, an 840K process-evaluation dataset, and a fine-tuned step-level evaluator shows current MLLMs solve under 60% of questions and make frequent reasoning errors.
Olympicarena: Benchmarking multi-discipline cognitive reasoning for superintelligent ai
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
K12Vista: Exploring the Boundaries of MLLMs in K-12 Education
A new Chinese K-12 multimodal benchmark with 33,660 questions, an 840K process-evaluation dataset, and a fine-tuned step-level evaluator shows current MLLMs solve under 60% of questions and make frequent reasoning errors.