Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1227 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Offline Reinforcement Learning | Adroit Door (target-domain) | 24 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Adroit Pen (target-domain) | 24 | Feb 26, 2026 | ||
| Jailbreaking | ConceptRisk | 24 | Feb 26, 2026 | ||
| Jailbreaking | COCO-I2VSafetyBench | 24 | Feb 26, 2026 | ||
| Automatic Speech Recognition | CHIME-4 Real (test) | 24 | Feb 26, 2026 | ||
| Cinematic Story Generation | ViStoryBench | 24 | Feb 26, 2026 | ||
| Engineering Design | EngDesign Extended | 24 | Feb 26, 2026 | ||
| Engineering Design | EngDesign Core | 24 | Feb 26, 2026 | ||
| Scientific Problem Solving | SciBench-107 | 24 | Feb 26, 2026 | ||
| Code Safety Evaluation | BigCodeBench 1.0 (test) | 24 | Feb 26, 2026 | ||
| Medical Image Segmentation | BTMRI (Source) | 24 | Mar 19, 2026 | ||
| Ownership Verification | Model Extraction Setting Surrogate Models | 24 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 | 24 | Feb 26, 2026 | ||
| OOD Detection | Far-OOD (test) | 24 | Apr 30, 2026 | ||
| Click-Through Rate Prediction | iFly-AD standard (test) | 24 | Feb 26, 2026 | ||
| Click-Through Rate Prediction | Criteo standard (test) | 24 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 (test) | 24 | Feb 26, 2026 | ||
| Semantic Segmentation | PASTIS | 24 | Mar 10, 2026 | ||
| Machine Translation | WMT xx→en 24 | 24 | Feb 26, 2026 | ||
| Machine Translation | WMT en→xx 24 | 24 | Feb 26, 2026 | ||
| Machine Translation | FLORES-200 en→xx | 24 | Feb 26, 2026 | ||
| Collaborative Perception Attack | Adv-OPV2V 1.0 (test) | 24 | Feb 26, 2026 | ||
| Image Captioning | MS-COCO 1,000 images subset 2014 2017 (val) | 24 | Feb 26, 2026 | ||
| Object Detection | VisDrone (test-dev) | 24 | Jul 2, 2026 | ||
| Whole Slide Image Classification | TCGA Lung | 24 | Feb 26, 2026 |