Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1892 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Information Retrieval | QAMPARI N=1000 (test) | 18 | Feb 26, 2026 | ||
| Classification | Average across datasets | 18 | Mar 16, 2026 | ||
| Reasoning | r-GSM, Seven Objects, and Date | 18 | Feb 26, 2026 | ||
| Time Series Classification | ACSF1 (UCR) | 18 | Jun 23, 2026 | ||
| Biomedical Multi-hop Question Answering | BioASQ-B | 18 | Feb 26, 2026 | ||
| Biomedical Multi-hop Question Answering | MedHopQA | 18 | Feb 26, 2026 | ||
| Automatic Speech Recognition | YM (test) | 18 | Feb 26, 2026 | ||
| Entity Linking | AIDA-CoNLL Wikipedia 2019 (test) | 18 | Feb 26, 2026 | ||
| Action Recognition | MSR-Action3D (Protocol) | 18 | Feb 26, 2026 | ||
| Salient Object Detection | Efficiency Evaluation | 18 | Feb 26, 2026 | ||
| Multi-task Dense Prediction | PASCAL-Context (test) | 18 | Mar 30, 2026 | ||
| Object Detection | COCO Novel #20 2014/2017 (test) | 18 | Feb 26, 2026 | ||
| Object Detection | COCO Base #60 2014 2017 (test) | 18 | Feb 26, 2026 | ||
| Object Detection | COCO Overall #80 2014/2017 (test) | 18 | Feb 26, 2026 | ||
| Few-shot Image Classification | tieredImageNet original (test) | 18 | Feb 26, 2026 | ||
| Relative Depth Estimation | BLINK RelativeDepth (test) | 18 | Feb 26, 2026 | ||
| Named Entity Recognition | BC5CDR disease | 18 | Feb 26, 2026 | ||
| Named Entity Recognition | BC5CDR chem | 18 | Feb 26, 2026 | ||
| Classification | OfficeHome Rw→Ar,Cl,Pr | 18 | Feb 26, 2026 | ||
| Classification | OfficeHome Cl→Ar,Pr,Rw | 18 | Feb 26, 2026 | ||
| Classification | REFUGE (test) | 18 | Feb 26, 2026 | ||
| Classification | ADAM (test) | 18 | Feb 26, 2026 | ||
| Retinal Fundus Image Classification | FIVES | 18 | Feb 26, 2026 | ||
| Diabetic Macular Edema detection | IDRiD DME | 18 | Feb 26, 2026 | ||
| Classification | RFMiD (test) | 18 | Feb 26, 2026 |