Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2241 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| FetchReach | Gymnasium Robotics | 16 | Feb 26, 2026 | ||
| Button2 | Safety Gymnasium | 16 | Feb 26, 2026 | ||
| Button1 | Safety Gymnasium | 16 | Feb 26, 2026 | ||
| Goal2 | Safety Gymnasium | 16 | Feb 26, 2026 | ||
| Goal1 | Safety Gymnasium | 16 | Feb 26, 2026 | ||
| Classification | Amazon Employee Kaggle | 16 | Mar 12, 2026 | ||
| Text-to-Image Generation | ImageReward (test) | 16 | Feb 26, 2026 | ||
| Image Classification | MNIST-ST (test) | 16 | Feb 26, 2026 | ||
| Classification | Fast-Stim original (test) | 16 | Feb 26, 2026 | ||
| Medical Reasoning Grounding | U-MRG-14K (test) | 16 | Feb 26, 2026 | ||
| Medical Question Answering | NEJM | 16 | Mar 5, 2026 | ||
| Nightlight Prediction | NYC Target from CHI & SF | 16 | Feb 26, 2026 | ||
| Carbon Prediction | NYC Target from CHI & SF | 16 | Feb 26, 2026 | ||
| Population Prediction | NYC Target from CHI & SF | 16 | Feb 26, 2026 | ||
| Service Call Prediction | NYC Target from CHI & SF | 16 | Feb 26, 2026 | ||
| Crime Prediction | NYC Target from CHI & SF | 16 | Feb 26, 2026 | ||
| Layer-wise Selective Attack (LSA) Robustness | Federated Learning Dataset | 16 | Feb 26, 2026 | ||
| Layer-wise Poisoning Attack (LPA) Robustness | Federated Learning Dataset | 16 | Feb 26, 2026 | ||
| BadNets Backdoor Attack Robustness | Federated Learning Dataset | 16 | Feb 26, 2026 | ||
| Distributed Backdoor Attack (DBA) Robustness | Federated Learning Dataset | 16 | Feb 26, 2026 | ||
| ProCams simulation | Real-world Novel Viewpoints | 16 | Feb 26, 2026 | ||
| ProCams simulation | Real-world benchmark dataset Trained Viewpoints | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K (test) | 16 | Feb 26, 2026 | ||
| Short-Term Anticipation | Ego4D STA v2 (val) | 16 | Feb 26, 2026 | ||
| Depth Completion | Metropolis | 16 | Feb 26, 2026 |