Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 380 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Voiced/Unvoiced Detection | Speech | 50 | Feb 26, 2026 | ||
| Audio Deepfake Detection | Codecfake | 50 | Apr 30, 2026 | ||
| Robot Manipulation | Adroit | 50 | Apr 9, 2026 | ||
| Attribution Faithfulness Evaluation | SocialNetwork (test) | 50 | Feb 26, 2026 | ||
| Attribution Faithfulness Evaluation | TwinMarket (test) | 50 | Feb 26, 2026 | ||
| Attribution Faithfulness Evaluation | EconAgent (test) | 50 | Feb 26, 2026 | ||
| Classification | UCI Mice Protein (test) | 50 | May 12, 2026 | ||
| Function Selection | TinyAgent | 50 | Feb 26, 2026 | ||
| Forecasting | Bitcoin (test) | 50 | Feb 26, 2026 | ||
| Classification | 10 Datasets Missing rate > 10% (test) | 50 | Feb 26, 2026 | ||
| Wind power forecasting | 8 target wind farms aggregated (test) | 50 | Feb 26, 2026 | ||
| Online Reinforcement Learning | OpenAI Gym MuJoCo Normalized v4 | 50 | Feb 26, 2026 | ||
| Multiple-choice Question Answering | BoolQ | 50 | Jun 29, 2026 | ||
| Mathematical Reasoning | Math500 | 50 | Apr 14, 2026 | ||
| Multi-hop Question Answering | MusiQue | 50 | May 28, 2026 | ||
| Information Retrieval | TREC DL20 | 50 | Mar 17, 2026 | ||
| Virtual Try-On | VITON-HD unpaired | 50 | Jul 1, 2026 | ||
| Image Classification | Tiny-ImageNet 64x64, C=200 (val) | 50 | Feb 26, 2026 | ||
| 3D reconstruction | ETH3D | 50 | Jul 7, 2026 | ||
| 3D Building Reconstruction | NYC Urban Dataset | 50 | Feb 26, 2026 | ||
| Blind Image Quality Assessment | KonIQ-10k | 50 | Jun 2, 2026 | ||
| Video Understanding | VideoEvalPro (test) | 50 | Mar 31, 2026 | ||
| Video Understanding | MotionBench (val) | 50 | Mar 31, 2026 | ||
| AIGC Image Detection | AIGCDetect-Benchmark | 50 | May 29, 2026 | ||
| Pulse Rate Estimation | UBFC-rPPG to PURE (test) | 50 | Jun 4, 2026 |