Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 27 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Generalized Category Discovery | CIFAR-100 | 268 | Jul 2, 2026 | ||
| Semantic Segmentation | Pascal VOC (test) | 268 | May 13, 2026 | ||
| Science Question Answering | ARC-C | 268 | Jun 4, 2026 | ||
| Long Video Understanding | LVBench | 267 | Jul 8, 2026 | ||
| Hallucination Evaluation | AMBER | 267 | Jul 7, 2026 | ||
| Multivariate Time Series Forecasting | Exchange | 267 | Jun 11, 2026 | ||
| Backdoor Defense | Tiny ImageNet | 267 | Jul 8, 2026 | ||
| Out-of-Distribution Detection | SUN OOD with ImageNet-1k In-distribution (test) | 267 | Jun 25, 2026 | ||
| Mathematical Reasoning | MathVerse | 266 | Jul 9, 2026 | ||
| Traffic Forecasting | PEMS08 | 266 | Jun 12, 2026 | ||
| Long Video Understanding | MLVU | 265 | Jun 26, 2026 | ||
| Multimodal Model Evaluation | MMBench | 265 | Jul 3, 2026 | ||
| Reasoning | MMLU-Pro | 264 | Jun 11, 2026 | ||
| Visual Question Answering | InfoVQA | 264 | Jun 26, 2026 | ||
| Object Detection | MS-COCO 2017 (val) | 264 | Jun 23, 2026 | ||
| Image Classification | ImageNet LT | 264 | Jun 23, 2026 | ||
| Visual Grounding | RefCOCO+ (val) | 264 | Jul 3, 2026 | ||
| Multitask Language Understanding | MMLU | 263 | Jun 29, 2026 | ||
| Multimodal Math Reasoning | MathVision | 263 | Jun 11, 2026 | ||
| RGB-D Object Tracking | VOT-RGBD 2022 (public challenge) | 263 | Apr 15, 2026 | ||
| Human-Object Interaction Detection | HICO-DET | 263 | May 7, 2026 | ||
| Molecular property prediction | QM9 (test) | 263 | Jun 16, 2026 | ||
| Instruction Following | Arena Hard | 263 | Jun 2, 2026 | ||
| Jailbreak Attack | StrongREJECT | 262 | May 22, 2026 | ||
| 3D Visual Grounding | ScanRefer (val) | 262 | Jul 7, 2026 |