Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 438 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | TriviaQA | 46 | Feb 26, 2026 | ||
| Tool Calling | API-Bank L-1 | 46 | May 14, 2026 | ||
| Closed-loop Autonomous Driving | Bench2Drive closed-loop | 46 | Jun 12, 2026 | ||
| Adversarial Attack | ModelNet40 | 46 | Apr 14, 2026 | ||
| Trajectory Prediction | ETH/UCY (Eth) | 46 | May 22, 2026 | ||
| General Instruction Following | Arena-Hard | 46 | Mar 4, 2026 | ||
| Classification | Country | 46 | Jun 19, 2026 | ||
| Machine Unlearning | CIFAR-10 | 46 | Jun 4, 2026 | ||
| Arithmetic Reasoning | SVAMP, GSM8K, AddSub, MultiArith, AQUA, SingleEq | 46 | Apr 24, 2026 | ||
| End-to-End Autonomous Driving | Bench2Drive base set | 46 | Feb 26, 2026 | ||
| Prostate Segmentation | Prostate | 46 | Mar 27, 2026 | ||
| Correction | VISCO full 1.0 (test) | 46 | Feb 26, 2026 | ||
| Multiple Instance Learning Classification | MUSK2 | 46 | Jun 5, 2026 | ||
| Multiple Instance Learning Classification | MUSK1 | 46 | Jun 5, 2026 | ||
| Long-video Question Answering | MLVU | 46 | Jun 8, 2026 | ||
| Long-video Question Answering | Long VideoBench (val) | 46 | Jun 8, 2026 | ||
| Oriented Object Detection | DOTA v1.0 | 46 | Jun 5, 2026 | ||
| Node Classification | Aminer | 46 | May 18, 2026 | ||
| Mathematical Reasoning | MATHEMATICS | 46 | Apr 14, 2026 | ||
| Infographic Visual Question Answering | InfoVQA (test) | 46 | Jun 2, 2026 | ||
| Sentiment Classification | SST2 | 46 | Jun 5, 2026 | ||
| Time Series Imputation | ETTm2 (test) | 46 | Jul 9, 2026 | ||
| Time Series Imputation | ETTm1 (test) | 46 | Jul 9, 2026 | ||
| Open Vocabulary Semantic Segmentation | PASCAL VOC VOC21 with background 2012 | 46 | May 20, 2026 | ||
| Quantization | OPT | 46 | Feb 26, 2026 |