Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2681 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Distortion Identification | PANDABENCH Easy | 14 | Apr 14, 2026 | ||
| Hypergraph Node Classification | Senate (test) | 14 | Apr 14, 2026 | ||
| Panoptic Segmentation | ScanNet++ | 14 | Apr 14, 2026 | ||
| Panoptic Segmentation | ScanNet v2 | 14 | Apr 14, 2026 | ||
| Cardiac substructure segmentation | MMWHS CT to MRI (test) | 14 | Apr 14, 2026 | ||
| Information Retrieval | QASPER NLP | 14 | Jun 23, 2026 | ||
| GUI Task Completion | RISK-Bench (online) | 14 | Apr 14, 2026 | ||
| Object Detection | RGBTDronePerson | 14 | Apr 14, 2026 | ||
| Language Modeling | Tiny-Shakespeare | 14 | Apr 14, 2026 | ||
| Machine Unlearning | CIFAR-100 Non-IID (1% forget data) | 14 | Apr 14, 2026 | ||
| Object Detection | EMPIAR-10499 | 14 | Apr 14, 2026 | ||
| Object Detection | EMPIAR-10304 | 14 | Apr 14, 2026 | ||
| Object Detection | CZII | 14 | Apr 14, 2026 | ||
| Multimodal Understanding | MMSU | 14 | May 28, 2026 | ||
| Action Unit Detection | BP4D (5-fold cross-val) | 14 | Apr 14, 2026 | ||
| Factual consistency evaluation | 2,055 code summary evaluations | 14 | Apr 14, 2026 | ||
| Affective Image Manipulation | AIM | 14 | Apr 14, 2026 | ||
| Code Generation | SWE-bench Lite | 14 | Apr 14, 2026 | ||
| Bug localization | InfiniteBench-CodeDebug, DebugBench, and LongCodeQA | 14 | Apr 14, 2026 | ||
| Code Generation | LCA CodeGen (test) | 14 | Apr 14, 2026 | ||
| Multimodal Mathematical Reasoning | MathVerse | 14 | Apr 14, 2026 | ||
| General Reasoning & Understanding | MMStar | 14 | May 14, 2026 | ||
| Human Activity Recognition | HAR Average Across 8 Datasets | 14 | Apr 14, 2026 | ||
| Human Activity Recognition | DSADS Subject-Hold-Out | 14 | Apr 14, 2026 | ||
| Human Activity Recognition | WISDM Subject-Hold-Out | 14 | Apr 14, 2026 |