Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2086 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Climate Forecasting | ICAR-ENSO (test) | 17 | Feb 26, 2026 | ||
| Generalized Few-Shot Object Detection | MS-COCO 5-shot (test) | 17 | Feb 26, 2026 | ||
| Raw Image Reconstruction | AdobeFiveK (test) | 17 | Jun 24, 2026 | ||
| Semantic Segmentation | nuImages | 17 | Feb 26, 2026 | ||
| Per-segment sleep apnea detection | Apnea-ECG | 17 | Feb 26, 2026 | ||
| Object Detection | PASCAL VOC 07+12 (trainval) | 17 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL HalfCheetah medium-expert v2 | 17 | Jun 2, 2026 | ||
| Object Detection | V100 GPU (test) | 17 | Feb 26, 2026 | ||
| Sign Language Recognition | WLASL (test) | 17 | Feb 26, 2026 | ||
| Snitch Localization | CATER Snitch localization 1.0 (test) | 17 | Feb 26, 2026 | ||
| Named Entity Recognition | NER Average over all languages (test) | 17 | Jun 2, 2026 | ||
| Classification | MMLU (test) | 17 | Feb 26, 2026 | ||
| Generation | Big-Bench Hard (test) | 17 | Feb 26, 2026 | ||
| Multi-Person Pose Estimation | COCO 2017 (mini-val) | 17 | Feb 26, 2026 | ||
| Text-to-Audio Generation | Clotho (test) | 17 | Feb 26, 2026 | ||
| 3D Lane Detection | OpenLane | 17 | Feb 26, 2026 | ||
| Image Classification | ImageNet original (val) | 17 | Feb 26, 2026 | ||
| Speech Recognition | Common Voice | 17 | Feb 26, 2026 | ||
| Video Super-Resolution | RealMCVSR (test) | 17 | Feb 26, 2026 | ||
| Autonomous Driving | CARLA 42 routes | 17 | Feb 26, 2026 | ||
| Code Generation | ARCADE New Tasks | 17 | Feb 26, 2026 | ||
| Code Generation | ARCADE Existing Tasks | 17 | Feb 26, 2026 | ||
| Automatic Speech Recognition | AISHELL-2 iOS (test) | 17 | Mar 27, 2026 | ||
| Video Generation | UCF101 128x128 16 frames | 17 | Feb 26, 2026 | ||
| Video Question Answering | MSRVTT Open Ended (OE) | 17 | Feb 26, 2026 |