Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 93 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Zero-shot Evaluation | Arc-Challenge, Arc-Easy, HellaSwag, LAMBADA-openai, LAMBADA-standard, PIQA, and WinoGrande Zero-Shot | 123 | Jun 12, 2026 | ||
| Prompt Injection Defense | Inj-SQuAD | 123 | Apr 10, 2026 | ||
| Multimodal Model Evaluation | MME | 123 | Jun 24, 2026 | ||
| Robot Manipulation | SimplerEnv WidowX | 123 | Jul 7, 2026 | ||
| Human Response Prediction | Synthetic Persona Dataset | 123 | Feb 26, 2026 | ||
| Image Reconstruction | COCO 2017 (val) | 123 | Mar 26, 2026 | ||
| Object Hallucination Evaluation | POPE (test) | 123 | Jun 15, 2026 | ||
| Novel View Synthesis | MipNeRF 360 Outdoor | 123 | May 11, 2026 | ||
| Mathematical Reasoning | GSM8K | 123 | Mar 5, 2026 | ||
| Image Classification | Flowers102 (test) | 123 | Apr 28, 2026 | ||
| Video Instance Segmentation | YouTube-VIS 2019 | 123 | Jul 2, 2026 | ||
| Instance Segmentation | MS COCO | 123 | Jul 7, 2026 | ||
| Question Answering | NQ | 123 | Mar 5, 2026 | ||
| Image Super-resolution | Urban100 x2 (test) | 123 | Jun 19, 2026 | ||
| Question Answering | StrategyQA | 123 | Apr 23, 2026 | ||
| Time Series Classification | SelfRegulationSCP1 | 123 | May 18, 2026 | ||
| Out-of-Distribution Detection | CIFAR100 (test) | 123 | May 12, 2026 | ||
| Point Cloud Adversarial Attack | ModelNet40 (test) | 123 | Mar 20, 2026 | ||
| Object Detection | MS COCO novel classes 2017 (val) | 123 | Feb 27, 2026 | ||
| Image Classification | ANIMAL-10N (test) | 123 | May 21, 2026 | ||
| Sentiment Analysis | SST-5 | 123 | May 19, 2026 | ||
| Image Classification | ImageNet 16-120 NAS-Bench-201 (val) | 123 | May 22, 2026 | ||
| Clustering | CIFAR-100 (test) | 123 | Mar 26, 2026 | ||
| Active Speaker Detection | AVA-ActiveSpeaker (val) | 123 | Jul 7, 2026 | ||
| Skeleton-based Action Recognition | NTU-RGB+D (Cross-subject) | 123 | Feb 26, 2026 |