Standard 1 stop to get here · leads to 1
Benchmark
A standardized dataset and task used to compare model performance across different approaches (ImageNet, GLUE, SuperGLUE).
Your route here
1 stop · basics first
- Dataset ✓ understood
A collection of data examples used for training, validating, or testing machine learning models.
- Benchmark · you are here ✓ understood
Where it sits
Explore nearby
Evaluation Baseline Model A simple reference model (random, majority class, simple heuristic) used to benchmark more complex models against. Evaluation Benchmark Gaming Optimizing models specifically for benchmark performance rather than real-world capabilities, inflating scores artificially. Vision & Multimodal ImageNet A large-scale dataset of 14M images in 20K categories, historically used as the benchmark for image classification models. Evaluation Test Set A final portion of data unseen during training and validation, used for unbiased evaluation of model performance. Language & LLMs Emergent Abilities Capabilities that appear suddenly in large language models at certain scales, not present in smaller models.
In the research
All papers →7 papers that build on Benchmark ; showing 5, canon first.
Canon · 2009 ImageNet: A Large-Scale Hierarchical Image Database ImageNet and its annual challenge gave deep learning the benchmark it needed to prove itself. 
Canon · 2020 Measuring Massive Multitask Language Understanding It became the headline benchmark in LLM release notes for years, and a case study in benchmarks saturating. 
Frontier · Sep 2025 · 282 citations Why Language Models Hallucinate It reframes hallucination as an incentive problem baked into how we measure models, not a mystery. 
Frontier · Feb 2026 · 174 citations SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks It is the first careful evidence that skills work, and that smaller models with good skills can match bigger ones. 
Frontier · Oct 2025 · 108 citations GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks It measures economic usefulness directly, instead of exam-style puzzles.