Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 242 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Action Recognition | NTU RGB+D Xsub 60 (Cross-Subject 55/5) | 66 | May 22, 2026 | ||
| Troop placement prediction | Risk | 66 | Mar 31, 2026 | ||
| 3D Shape Matching | SCAPE Anisotropic (S_a) | 66 | Jun 26, 2026 | ||
| 3D Shape Matching | FAUST Anisotropic (F_a) | 66 | Jun 26, 2026 | ||
| Optical Illusion Character Recognition | IlluChar (Origin) | 66 | Mar 25, 2026 | ||
| Tracking | KITTI | 66 | Jun 24, 2026 | ||
| Deferral-advice | CLIP prompt-escalation (val) | 66 | Mar 17, 2026 | ||
| Definition Generation | Multi-word tokens famous people, places, entities, sayings and concepts | 66 | Mar 16, 2026 | ||
| Safety Evaluation | MultiJail | 66 | Mar 13, 2026 | ||
| Confidence Calibration | dermatology | 66 | Mar 12, 2026 | ||
| Visual Localization | 7Scenes | 66 | May 19, 2026 | ||
| Mathematical Reasoning | MGSM | 66 | Jun 25, 2026 | ||
| Time Series Forecasting | ETTm2 | 66 | Mar 10, 2026 | ||
| DNA-to-protein transduction | DNA sequence pdna (test) | 66 | Mar 6, 2026 | ||
| Truthful Question Answering | TruthfulQA MC2 | 66 | Jun 8, 2026 | ||
| Math Reasoning | MATH500 | 66 | May 22, 2026 | ||
| Image Understanding | MME | 66 | May 21, 2026 | ||
| 3D Reconstruction | NRGBD | 66 | May 12, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 ID CIFAR-100 OOD | 66 | May 26, 2026 | ||
| Multi-task Language Understanding | MMLU Pro | 66 | Jun 19, 2026 | ||
| Inference Attack | Federated Learning environments Unauthorized Access (test) | 66 | Feb 26, 2026 | ||
| Inference Attack | Federated Learning environments Authorized Access (test) | 66 | Feb 26, 2026 | ||
| Text-to-Speech | LibriSpeech PC clean (test) | 66 | Jun 16, 2026 | ||
| Suffix Ranking | Extraction Challenge Dataset | 66 | Feb 26, 2026 | ||
| Numerical Reasoning | RealHitBench | 66 | Apr 15, 2026 |