GAIA benchmark shows humans at 92% accuracy on simple real-world questions far outperform current AI systems at 15%, proposing this gap as a key milestone for general AI.
InProceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’23)
2 Pith papers cite this work, alongside 62 external citations. Polarity classification is still indexing.
2
Pith papers citing it
62
external citations · external index
verdicts
UNVERDICTED 2representative citing papers
Among 919 intro CS students solving Prompt Problems, typed prompts beat unedited voice on first-attempt success for two of three tasks; edited voice matched text, and most preferred text.
citing papers explorer
-
GAIA: a benchmark for General AI Assistants
GAIA benchmark shows humans at 92% accuracy on simple real-world questions far outperform current AI systems at 15%, proposing this gap as a key milestone for general AI.
-
Say What? Examining Text and Voice Input Modalities for Prompt-Based Programming in Computing Education
Among 919 intro CS students solving Prompt Problems, typed prompts beat unedited voice on first-attempt success for two of three tasks; edited voice matched text, and most preferred text.