Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1584 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Fluid Flow Generative Modeling | Kolmogorov Flow | 20 | Apr 8, 2026 | ||
| Long-video Question Answering | LV-Bench (val) | 20 | Apr 8, 2026 | ||
| Text Completion | OpenGen | 20 | Apr 8, 2026 | ||
| Text Completion | Essays | 20 | Apr 8, 2026 | ||
| Heterogeneous Fleet Vehicle Routing Problem | HFCVRP (N=80, K=30) | 20 | Apr 8, 2026 | ||
| Heterogeneous Fleet Open Vehicle Routing Problem | HFOVRP N=50, K=20 (test) | 20 | Apr 8, 2026 | ||
| Heterogeneous Fleet Capacitated Vehicle Routing Problem | HFCVRP (N=50, K=20) (test) | 20 | Apr 8, 2026 | ||
| Attack Success Rate Evaluation | Hot100 | 20 | Apr 8, 2026 | ||
| Visual Question Answering | VQA v2 | 20 | Apr 8, 2026 | ||
| Multimodal Evaluation | MME | 20 | Apr 8, 2026 | ||
| Cerebral Lesion Segmentation | SBM | 20 | May 1, 2026 | ||
| Medical Question Answering | MedQA 4-option original (test) | 20 | Apr 8, 2026 | ||
| Step success rate | AndroidControl Task-Unseen | 20 | Apr 8, 2026 | ||
| Language Modeling | SST | 20 | Apr 7, 2026 | ||
| Boolean Question Answering | BoolQ | 20 | May 4, 2026 | ||
| Dialectal alignment estimation | ELI5 informal | 20 | Apr 7, 2026 | ||
| Dialectal alignment estimation | Natural Questions (NQ) (formal) | 20 | Apr 7, 2026 | ||
| Video-level Deepfake Detection | FaceForensics++ (FF++) (test) | 20 | Apr 7, 2026 | ||
| Regression | UCI Yacht | 20 | Jun 15, 2026 | ||
| 3D Object Detection | DSERT-RoLL official (test) | 20 | Apr 7, 2026 | ||
| Video Retrieval | TVR (evaluation) | 20 | Apr 7, 2026 | ||
| Pedestrian Trajectory Prediction | ETH UCY | 20 | Apr 7, 2026 | ||
| PDE Solving | Elasticity Point Cloud (test) | 20 | May 12, 2026 | ||
| Selective Prediction | SAMSum | 20 | Apr 7, 2026 | ||
| Selective Prediction | WMT ru 19 | 20 | Apr 7, 2026 |