Artificial Intelligence
33 views
AI Benchmark
Quick Definition
Standardized tests measuring AI model performance
Full Definition
Standardized tests measuring AI model performance across specific tasks and capabilities.
Examples
GLUE, SuperGLUE, ImageNet, MMLU, HumanEval
Related Terms
model-evaluation
performance-metrics
More Artificial Intelligence Terms
Bag of Words
Text model representing documents by word frequency counts
Reward Modeling
Training models to predict human preferences for RLHF
Style Transfer
Applying artistic style of one image to another using neural networks
Named Entity Recognition
Identifying and classifying named entities in text
Neural Architecture Search
Automating the design of optimal neural network architectures
Symbolic AI
AI using symbolic logic and explicit knowledge rules