Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 739 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Empathy evaluation | E-Dialogue | 33 | Feb 26, 2026 | ||
| Tabular Data Synthesis | texture | 33 | Feb 26, 2026 | ||
| Molecular property prediction | MOLTOX21 | 33 | May 25, 2026 | ||
| Medical Image Classification | SC (Skin Cancer) (test) | 33 | Feb 26, 2026 | ||
| Human Activity Recognition | USC-HAD | 33 | Jul 7, 2026 | ||
| Unsupervised Object Discovery | PASCAL VOC 2007 | 33 | Apr 15, 2026 | ||
| Federated Out-of-Distribution Detection | CIFAR-100 (ID) and LSUN-C (OOD) (test) | 33 | Feb 26, 2026 | ||
| Federated Image Classification | CIFAR-100 and CIFAR-100-C brightness (test) | 33 | Feb 26, 2026 | ||
| Point Tracking | TAP-Vid DAVIS (Strided) | 33 | Mar 31, 2026 | ||
| Machine Translation Meta-evaluation | WMT Metrics Shared Task Segment-level 2023 (Primary submissions) | 33 | Feb 26, 2026 | ||
| Object Detection | SARDet-100K (test) | 33 | Mar 4, 2026 | ||
| Multivariate Time Series Forecasting | ILI | 33 | May 26, 2026 | ||
| Instruction Following | Instruction Following Evaluation Suite | 33 | Feb 26, 2026 | ||
| Natural Language Processing tasks | MTI BENCH | 33 | Feb 26, 2026 | ||
| Truthfulness Evaluation | TruthfulQA | 33 | Apr 9, 2026 | ||
| Code Generation | HumanEval Python | 33 | Jun 4, 2026 | ||
| Language Modeling and Reasoning | Open LLM Leaderboard | 33 | Feb 26, 2026 | ||
| Motion-to-text retrieval | HumanML3D (test) | 33 | Mar 26, 2026 | ||
| Semantic Segmentation | semanticKITTI SynLiDAR source (val) | 33 | Mar 20, 2026 | ||
| 3D Object Detection | KITTI-360 (val) | 33 | Jun 9, 2026 | ||
| Generalized Referring Expression Segmentation | gRefCOCO v1 (val) | 33 | Feb 26, 2026 | ||
| Video Reconstruction | DAVIS | 33 | Jun 12, 2026 | ||
| Code Completion | MBPP+ | 33 | Feb 26, 2026 | ||
| Code Completion | HumanEval+ | 33 | Feb 26, 2026 | ||
| Domain Generalization | DomainBed (OH, TI, VLCS, PACS, DN) (test) | 33 | Feb 26, 2026 |