Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 631 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Evaluation | MMMU | 36 | May 15, 2026 | ||
| Soft constrained reward optimization | XSum on Gemma-7B | 36 | May 15, 2026 | ||
| Pareto prompt set identification | CNN/DailyMail | 36 | May 15, 2026 | ||
| Positive-Unlabeled Classification | 14 imbalanced datasets SCAR assumption macro-averaged | 36 | May 15, 2026 | ||
| Time Series Forecasting | Stock Market | 36 | May 15, 2026 | ||
| Time Series Forecasting | Zillow Real Estate | 36 | May 15, 2026 | ||
| Image Classification | MEDIC subset | 36 | May 15, 2026 | ||
| Few-Shot Classification | FC-100 | 36 | May 15, 2026 | ||
| Few-shot Image Classification | AIDER subset simulation | 36 | May 15, 2026 | ||
| LiDAR semantic segmentation | SemanticKITTI | 36 | May 14, 2026 | ||
| Clustering | BANK-40K | 36 | May 14, 2026 | ||
| Clustering | CENSUS 1990 | 36 | May 14, 2026 | ||
| Mathematical Reasoning | Numina | 36 | May 14, 2026 | ||
| Air Quality Data Estimation | Real-world air quality dataset (test) | 36 | May 14, 2026 | ||
| Time Series Forecasting | ETTh1 (10% train) | 36 | May 19, 2026 | ||
| Binary classification | CTAF-KHAF Synthetic (test) | 36 | May 13, 2026 | ||
| Multimodal Reasoning | Medical and Mathematical Multimodal Reasoning SLAKE, VQA-Rad, Geo3K | 36 | May 13, 2026 | ||
| Reward Modeling | PPE-P | 36 | May 13, 2026 | ||
| Reward Modeling | RewardBench | 36 | May 13, 2026 | ||
| Model Editing | FEVER 20K edits (test) | 36 | May 13, 2026 | ||
| Lifelong Model Editing | ULTRAEDITBENCH | 36 | May 13, 2026 | ||
| Classification | pol | 36 | May 13, 2026 | ||
| LLM Inference Acceleration | MT-bench | 36 | May 13, 2026 | ||
| Link Prediction | ca-HepTh | 36 | May 13, 2026 | ||
| Structured Distribution Sampling | Seen distribution families unseen parameter settings | 36 | May 13, 2026 |