Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2196 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video Question Answering | VideoMME | 16 | Apr 8, 2026 | ||
| Video Question Answering | MLVU (test) | 16 | Apr 8, 2026 | ||
| Video Question Answering | LongVideoBench w/o sub. (val) | 16 | Apr 8, 2026 | ||
| Literature Review Quality Assessment | PaperWritingBench | 16 | Apr 8, 2026 | ||
| Robot Manipulation | RoboCasa-GR1 24 tasks | 16 | Apr 30, 2026 | ||
| Knowledge-based VQA | E-VQA | 16 | Apr 8, 2026 | ||
| Multimodal Classification | CrisisMMD | 16 | Apr 8, 2026 | ||
| Autoformalization | ConNF | 16 | Apr 8, 2026 | ||
| Logical Reasoning | RepublicQA | 16 | Apr 8, 2026 | ||
| Breast lesion malignancy diagnosis | Breast lesion candidates for biopsy (all cohorts) | 16 | Apr 8, 2026 | ||
| EEG Classification | Emotiv Crowdsourced | 16 | Apr 8, 2026 | ||
| Time-series forecasting | Uber TLC | 16 | Apr 8, 2026 | ||
| Time-series forecasting | NN5 Benchmark I | 16 | Apr 8, 2026 | ||
| Time-series forecasting | Covid Deaths Benchmark I | 16 | Apr 8, 2026 | ||
| Time-series forecasting | FRED-MD Benchmark I | 16 | Apr 8, 2026 | ||
| Time-series forecasting | ETTh1 Benchmark I | 16 | Apr 8, 2026 | ||
| Time-series forecasting | Traffic Benchmark I | 16 | Apr 8, 2026 | ||
| Time-series forecasting | Weather Benchmark I | 16 | Apr 8, 2026 | ||
| 3D Semantic Segmentation | ScanNet++ (val) | 16 | Apr 7, 2026 | ||
| Backdoor Attack | DriveVLM Base (test) | 16 | Apr 7, 2026 | ||
| Backdoor Attack | DriveVLM Large | 16 | Apr 7, 2026 | ||
| Language Modeling | WikiText (WT) | 16 | Apr 7, 2026 | ||
| Long-term Forecasting | Exchange 5% few-shot | 16 | Apr 7, 2026 | ||
| Video-level Deepfake Detection | DeepFake Detection Challenge (DFDC) (test) | 16 | Apr 7, 2026 | ||
| Stroke Diagnosis | Stroke Diagnosis Dataset | 16 | Apr 7, 2026 |