Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 864 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Automatic Speech Recognition | CHiME3 Single | 30 | Feb 26, 2026 | ||
| Anomalous Sound Detection | DCASE ASD 2020-2025 (dev and evaluation) | 30 | Feb 26, 2026 | ||
| Denoising | AFHQ Cat (test) | 30 | May 12, 2026 | ||
| Open-Set Recognition | Caltech-UCSD-Birds (CUB) Easy split 42 (test) | 30 | Feb 26, 2026 | ||
| Information Retrieval | WebQuestionsSP N=1639 (test) | 30 | Feb 26, 2026 | ||
| Information Retrieval | QUEST N=1727 (test) | 30 | Feb 26, 2026 | ||
| Medical Image Classification | NoduleMNIST3D | 30 | Jun 4, 2026 | ||
| Hallucination Detection | RAGTruth & HalluRAG Overall Average 1.0 (test) | 30 | Feb 26, 2026 | ||
| Hallucination Detection | HalluRAG 1.0 (test) | 30 | Feb 26, 2026 | ||
| Hallucination Detection | RAGTruth RT-Summ 1.0 (test) | 30 | Feb 26, 2026 | ||
| Hallucination Detection | RAGTruth RT-D2T 1.0 (test) | 30 | Feb 26, 2026 | ||
| Multi-view Clustering | 100leaves | 30 | Feb 26, 2026 | ||
| Multi-view Clustering | Hdigit | 30 | Feb 26, 2026 | ||
| Multi-view Clustering | Caltech101 20 | 30 | Feb 26, 2026 | ||
| Point Cloud Registration | ModelNet40 twice-sampled (TS) unseen categories (test) | 30 | Feb 26, 2026 | ||
| Anomaly Detection | Avenue | 30 | Feb 26, 2026 | ||
| Few-shot Image Classification | miniImageNet original (test) | 30 | Feb 26, 2026 | ||
| Class-Incremental Learning | CIFAR-100 20 tasks (test) | 30 | Mar 4, 2026 | ||
| Active Directory domain escalation | GOAD 5 hosts | 30 | Feb 26, 2026 | ||
| End-to-end penetration testing | PentestGPT Ben 13 machines | 30 | Feb 26, 2026 | ||
| Anomaly Detection | PSM | 30 | Jul 2, 2026 | ||
| Mathematical Reasoning | AMC23 | 30 | Mar 4, 2026 | ||
| Question Answering Task | ARC-C (test) | 30 | Jun 30, 2026 | ||
| Explainability classification | Toxic-Chat 0124 (test) | 30 | Feb 26, 2026 | ||
| Segmentation | ISIC 2018 | 30 | Apr 13, 2026 |