Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1645 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Instruction Following | AlpacaEval Swahili | 20 | Feb 26, 2026 | ||
| Instruction Following | AlpacaEval Indonesian | 20 | Feb 26, 2026 | ||
| Instruction Following | AlpacaEval Korean | 20 | Feb 26, 2026 | ||
| Instruction Following | AlpacaEval German | 20 | Feb 26, 2026 | ||
| Instruction Following | AlpacaEval Chinese | 20 | Feb 26, 2026 | ||
| Composed Person Retrieval | SynCPR (test) | 20 | Feb 26, 2026 | ||
| Autonomous Driving | Bench2Drive 220 routes across CARLA towns | 20 | Feb 26, 2026 | ||
| Sentiment Analysis | SST2 | 20 | Feb 26, 2026 | ||
| Multi-step mathematical reasoning | We-Math (test) | 20 | Feb 26, 2026 | ||
| Text-to-Image Retrieval | DeepFashion (test) | 20 | Feb 26, 2026 | ||
| Visual Spatial Reasoning | What's Up (Split B) | 20 | Feb 26, 2026 | ||
| Visual Spatial Reasoning | What's Up (Split A) | 20 | Feb 26, 2026 | ||
| Anomaly Segmentation | Kvasir | 20 | Apr 14, 2026 | ||
| Depth Estimation | Co3D Individual Scenes | 20 | Feb 26, 2026 | ||
| Stereo Matching | Middlebury non-occluded | 20 | Feb 26, 2026 | ||
| Image Restoration | DRealsr | 20 | Mar 24, 2026 | ||
| Micro-action Recognition | MA-52 1.0 (test) | 20 | Feb 26, 2026 | ||
| Long-term forecasting | ETTm2 T=336 | 20 | May 12, 2026 | ||
| Long-term forecasting | ETTm1 T=336 | 20 | May 12, 2026 | ||
| Long-term forecasting | ETTm1 T=192 | 20 | May 12, 2026 | ||
| Long-term forecasting | Weather T=720 | 20 | May 12, 2026 | ||
| Closed-set Source-Free Domain Adaptation | Office-Home Closed-set (test) | 20 | Feb 26, 2026 | ||
| Relative Pose Estimation | KITTI (Sequence 01) | 20 | Apr 7, 2026 | ||
| Monocular Depth Estimation | KITTI 16 (Eigen split) | 20 | Feb 26, 2026 | ||
| Synthetic Data Generation | IMDB (test) | 20 | Jun 23, 2026 |