Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2533 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Detection | CIFAR-10 6 classes | 15 | Feb 26, 2026 | ||
| Multimodal Benchmarking | MMMU | 15 | Feb 26, 2026 | ||
| General Knowledge Evaluation | C-Eval (val) | 15 | Apr 23, 2026 | ||
| Multimodal Understanding | SEED Benchmark (test) | 15 | Apr 9, 2026 | ||
| Image Classification | CIFAR-100 | 15 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 | 15 | Feb 26, 2026 | ||
| Question Answering | Counterfacts | 15 | Feb 26, 2026 | ||
| Object Detection | Objects365 (test) | 15 | Jun 5, 2026 | ||
| Machine Translation | IWSLT 2017 (test) | 15 | Feb 26, 2026 | ||
| Language generation | C4 (val) | 15 | Feb 26, 2026 | ||
| 3D Multi-Object Tracking | Waymo (test) | 15 | Feb 26, 2026 | ||
| Video Action Recognition | SS v2 | 15 | Feb 26, 2026 | ||
| Text Generation | Alpaca | 15 | Jun 2, 2026 | ||
| Unsupervised Constituency Parsing | English SPMRL (test) | 15 | Feb 26, 2026 | ||
| Optical Character Recognition | Ancient Greek | 15 | Feb 26, 2026 | ||
| Multimodal Understanding | SEED-Bench 1 | 15 | Feb 26, 2026 | ||
| Skeleton-based Action Recognition | NTU RGB+D X-View60 | 15 | Feb 26, 2026 | ||
| Video Object Segmentation | ReVOS 1.0 (test) | 15 | Feb 26, 2026 | ||
| Question Answering | Medbullets-4 | 15 | Feb 26, 2026 | ||
| Referring Expression Segmentation | RefCOCOg Google (val) | 15 | Apr 10, 2026 | ||
| Spatial Understanding | SEED-Bench Spatial | 15 | Feb 26, 2026 | ||
| Visual Question Answering | A-OKVQA Open-Ended | 15 | Feb 26, 2026 | ||
| Multi-hop Reasoning | CommaQA-E compositional | 15 | Feb 27, 2026 | ||
| Multi-hop Reasoning | CommaQA-E (test) | 15 | Feb 27, 2026 | ||
| Generic Segmentation | FIND-Bench | 15 | Feb 26, 2026 |