Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1310 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text-to-Image | MS-COCO 5K prompts 2014 (val) | 23 | Feb 26, 2026 | ||
| Recommendation | Amazon Beauty (test) | 23 | Jun 30, 2026 | ||
| Question Answering | HotpotQA In-Distribution | 23 | May 15, 2026 | ||
| Multi-task Language Understanding | MMSU | 23 | May 8, 2026 | ||
| Offline Reinforcement Learning | D4RL Antmaze medium-play | 23 | Mar 4, 2026 | ||
| Node classification | Pubmed | 23 | May 4, 2026 | ||
| Spatial Reasoning | SPAR-Bench full | 23 | Mar 10, 2026 | ||
| Handwritten Text Recognition | IAM Aachen (test) | 23 | Feb 26, 2026 | ||
| Commonsense Reasoning | Hella Swag | 23 | Feb 26, 2026 | ||
| Polyp Segmentation | Kvasir-SEG CVC-ClinicDB (test) | 23 | Mar 6, 2026 | ||
| Node Classification | Citeseer HOMO. (test) | 23 | Jun 1, 2026 | ||
| Gene expression prediction | HestBench | 23 | Mar 10, 2026 | ||
| Flowchart-Oriented Dialogue | FLODIAL Overall 1.0 | 23 | Feb 26, 2026 | ||
| Flowchart-Oriented Dialogue | FLODIAL 1.0 (Middle-init) | 23 | Feb 26, 2026 | ||
| Flowchart-Oriented Dialogue | FLODIAL 1.0 (Root-init) | 23 | Feb 26, 2026 | ||
| Mathematical Reasoning | Math500 | 23 | Mar 10, 2026 | ||
| Primary/Metastatic Classification | Lung Cancer External cohort H6 | 23 | Feb 26, 2026 | ||
| Primary/Metastatic Classification | Lung Cancer External cohort H5 | 23 | Feb 26, 2026 | ||
| Primary/Metastatic Classification | Lung Cancer Internal cohort H1 | 23 | Feb 26, 2026 | ||
| Intestinal Metaplasia Classification | gastric cancer H7 (internal cohort) | 23 | Feb 26, 2026 | ||
| Normal/Abnormal Classification | gastric cancer H7 (internal cohort) | 23 | Feb 26, 2026 | ||
| pTNM Overall Staging (I/II/III) | Breast Cancer Internal Cohort H2 (internal evaluation) | 23 | Feb 26, 2026 | ||
| CK5 status prediction | Breast cancer H2 (internal cohort) | 23 | Feb 26, 2026 | ||
| HER2 status prediction | Breast cancer H2 (internal cohort) | 23 | Feb 26, 2026 | ||
| Progesterone Receptor (PR) status prediction | Breast cancer H2 (internal cohort) | 23 | Feb 26, 2026 |