Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 260 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | ImageNet 1K (val) | 64 | Apr 23, 2026 | ||
| Video Quality Assessment | LIVE-YT-Gaming | 64 | May 21, 2026 | ||
| Offline Reinforcement Learning | D4RL Hopper-medium-replay v2 | 64 | Jun 2, 2026 | ||
| Document Question Answering | DocVQA | 64 | May 26, 2026 | ||
| Adversarial Attack | ImageNet 21k (test) | 64 | Feb 26, 2026 | ||
| Adversarial Attack | Tiny-ImageNet (val) | 64 | Feb 26, 2026 | ||
| Few-shot Segmentation | FSS-1000 (test) | 64 | Jun 29, 2026 | ||
| Person Re-Identification | Occluded-DukeMTMC | 64 | Mar 20, 2026 | ||
| Natural Language Inference | ANLI Round 3 | 64 | Feb 26, 2026 | ||
| Natural Language Inference | ANLI Round 2 | 64 | Feb 26, 2026 | ||
| Unconditional Text Generation | EMNLP 2017 WMT News | 64 | Feb 26, 2026 | ||
| Trajectory Prediction | SDD | 64 | May 18, 2026 | ||
| Text-to-Image Generation | MS-COCO 256x256 (val) | 64 | May 27, 2026 | ||
| Scene Flow Estimation | KITTI | 64 | Jun 2, 2026 | ||
| Image Classification | ImageNet-A (val) | 64 | May 14, 2026 | ||
| Data-to-Text Generation | DART (test) | 64 | Jun 1, 2026 | ||
| Anomaly Detection | Satimage 2 | 64 | Jun 15, 2026 | ||
| Object Detection | COCO standard 2017 (train val) | 64 | Feb 26, 2026 | ||
| Pronoun Resolution | WinoGrande | 64 | Jun 18, 2026 | ||
| Action Anticipation | Breakfast | 64 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | iNaturalist (test) | 64 | May 11, 2026 | ||
| Image Classification | ImageNet Real 1k (val) | 64 | Feb 26, 2026 | ||
| Automatic Speech Recognition | LibriSpeech 100h (test-clean) | 64 | Jun 11, 2026 | ||
| Joint Entity and Relation Extraction | NYT (test) | 64 | Feb 26, 2026 | ||
| Object Detection | PASCAL VOC to Water Color (test) | 64 | Feb 26, 2026 |