Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

309,131 indexed

Task	Dataset	Domain	Results	Last Update
Multimodal Evaluation	MMMU	multimodal	36	May 15, 2026
Soft constrained reward optimization	XSum on Gemma-7B	nlpllm chat instruction	36	May 15, 2026
Pareto prompt set identification	CNN/DailyMail	nlpllm chat instruction	36	May 15, 2026
Positive-Unlabeled Classification	14 imbalanced datasets SCAR assumption macro-averaged	tabular time series	36	May 15, 2026
Time Series Forecasting	Stock Market	tabular time series