Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1503 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | ImageNet 1k (val) | 21 | Feb 26, 2026 | ||
| Multi-hop Question Answering | HotpotQA 10 related documents | 21 | Feb 26, 2026 | ||
| Multivariate Time Series Forecasting | NN5 | 21 | Apr 14, 2026 | ||
| Science Question Answering | ScienceQA IMG 38 | 21 | Feb 26, 2026 | ||
| Medical Image Classification | BreaKHis | 21 | Apr 15, 2026 | ||
| Composed Image Retrieval | CIRR v1.0 | 21 | Feb 26, 2026 | ||
| Calibration Testing | Synthetic dataset (test) | 21 | Feb 26, 2026 | ||
| Procedure Planning | COIN T=4 (test) | 21 | Mar 11, 2026 | ||
| Safety Evaluation | SafetyBench zh | 21 | Feb 26, 2026 | ||
| Long-Tailed Multi-Label Visual Recognition | COCO Long-Tailed (test) | 21 | Feb 26, 2026 | ||
| Class-conditional video generation | UCF-101 v1.0 (train test) | 21 | Feb 26, 2026 | ||
| General Performance | VicunaEval | 21 | Feb 26, 2026 | ||
| General LLM Evaluation | Open LLM Leaderboard (test) | 21 | Mar 4, 2026 | ||
| Keyphrase Generation | KPTimes (test) | 21 | Feb 26, 2026 | ||
| Multi-image Reasoning | DEMON | 21 | Feb 26, 2026 | ||
| Sentiment Analysis | IMDB | 21 | Feb 26, 2026 | ||
| Sentiment Analysis | Yelp Polarity | 21 | Feb 26, 2026 | ||
| Emotion Recognition | EMO | 21 | Feb 26, 2026 | ||
| Question Answering | MedQA (dev) | 21 | Feb 26, 2026 | ||
| Scene Classification | RESISC-45 Standard (20% train and 80% test) | 21 | Feb 26, 2026 | ||
| Image Classification | ImageNet New classes | 21 | Feb 26, 2026 | ||
| Medical Report Generation | MIMIC-CXR 2.0.0 (test) | 21 | Feb 26, 2026 | ||
| Arithmetic Tree Generation | 64-bit Adder | 21 | Feb 26, 2026 | ||
| Sleep Stage Classification | ISRUC-Sleep | 21 | Feb 26, 2026 | ||
| Commonsense Question Answering | WinoGrande (WG) (val) | 21 | Feb 26, 2026 |