Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2573 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Keyphrase Extraction | SemEval Task 10 ScienceIE 2017 (test) | 15 | Feb 26, 2026 | ||
| Image Generation | CAT 64x64 (N=9304) | 15 | Feb 26, 2026 | ||
| Answer Sentence Selection | SelQA (test) | 15 | Feb 26, 2026 | ||
| Reading Comprehension | SQuAD (dev) | 15 | Feb 26, 2026 | ||
| Activity Recognition | EGTEA Gaze+ (Split 3) | 15 | Feb 26, 2026 | ||
| Activity Recognition | EGTEA Gaze+ (Split 2) | 15 | Feb 26, 2026 | ||
| Activity Recognition | EGTEA Gaze+ (Split 1) | 15 | Feb 26, 2026 | ||
| Human Pose Tracking | JHMDB (val) | 15 | Feb 26, 2026 | ||
| Object Recognition | ImageNet CLS-LOC first 1,000 images (val) | 15 | Feb 26, 2026 | ||
| Lesion Segmentation | LiTS 2017 (test) | 15 | Feb 26, 2026 | ||
| Reinforcement Learning | Atari-57 (test) | 15 | Feb 26, 2026 | ||
| Machine Translation (Chinese-to-English) | NIST MT-06 | 15 | Feb 26, 2026 | ||
| Machine Translation (Chinese-to-English) | NIST MT 2004 | 15 | Feb 26, 2026 | ||
| Summarization | CNN/Daily Mail anonymized (test) | 15 | Feb 26, 2026 | ||
| Monocular Depth Estimation | KITTI online server (test) | 15 | Feb 26, 2026 | ||
| Action Alignment | Hollywood Extended | 15 | Feb 26, 2026 | ||
| Few-shot embedding induction | Chimera 1.0 (test) | 15 | Feb 26, 2026 | ||
| JPEG Image Artifacts Removal | LIVE1 (test) | 15 | Feb 26, 2026 | ||
| Single Image Super-Resolution | Set14 (test) | 15 | Feb 26, 2026 | ||
| Deblurring | GOPRO dataset | 15 | Feb 26, 2026 | ||
| Gesture Recognition | ChaLearn (val) | 15 | Feb 26, 2026 | ||
| Few-shot classification | ImageNet Novel categories (test) | 15 | Feb 26, 2026 | ||
| Entity Linking | WebQSP All entities (test) | 15 | Feb 26, 2026 | ||
| Speech Recognition | DIRHA English WSJ (real) | 15 | Feb 26, 2026 | ||
| Survival Analysis | CRC | 15 | Feb 26, 2026 |