Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 17 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Object Tracking | GOT-10k | 357 | Jul 3, 2026 | ||
| Time Series Forecasting | Weather (test) | 355 | Jun 19, 2026 | ||
| Node Classification | amazon-ratings | 354 | Jun 25, 2026 | ||
| Science Question Answering | ARC Challenge | 354 | May 12, 2026 | ||
| Mathematical reasoning | MathQA | 354 | May 25, 2026 | ||
| Image Classification | ImageNet (val) | 354 | Feb 26, 2026 | ||
| Referring Expression Comprehension | RefCOCO+ (val) | 354 | Jul 7, 2026 | ||
| Super-Resolution | BSD100 | 354 | Jul 7, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 353 | Jun 16, 2026 | ||
| Multi-task Language Understanding | MMLU | 353 | Apr 23, 2026 | ||
| Multi-Object Tracking | SportsMOT (test) | 353 | Jul 2, 2026 | ||
| Semantic Segmentation | SemanticKITTI (test) | 353 | May 29, 2026 | ||
| Node classification | Squirrel (test) | 353 | Jun 8, 2026 | ||
| Audio Watermarking Attribution | MusicCaps | 352 | May 25, 2026 | ||
| Mathematical Reasoning | GSM8K | 352 | Jun 25, 2026 | ||
| 3D Human Mesh Recovery | 3DPW (test) | 352 | Jun 23, 2026 | ||
| Single Image Super-Resolution | Set5 | 352 | Feb 26, 2026 | ||
| Image Classification | CUB | 351 | Jun 23, 2026 | ||
| Referring Expression Comprehension | RefCOCO (testA) | 351 | Jul 7, 2026 | ||
| Human Pose Estimation | MPII (test) | 350 | Mar 4, 2026 | ||
| Boolean Question Answering | BoolQ | 350 | Apr 23, 2026 | ||
| OCR Evaluation | OCRBench | 350 | Jun 2, 2026 | ||
| Anomaly Detection | SWaT | 348 | Jun 23, 2026 | ||
| Object Detection | COCO 2017 | 348 | Jul 7, 2026 | ||
| Referring Expression Comprehension | RefCOCO (val) | 348 | Jul 7, 2026 |