Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 730 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | MNIST LQ-1 partition (test) | 33 | Feb 27, 2026 | ||
| Image Classification | FMNIST | 33 | Mar 10, 2026 | ||
| Video Understanding | VideoMME, LongVideoBench, and MLVU | 33 | Jun 2, 2026 | ||
| Image Classification | ImageNet-50 | 33 | Feb 27, 2026 | ||
| Image Classification | ImageNet | 33 | Jun 2, 2026 | ||
| OCR Evaluation | OCRBench 1.0 | 33 | Feb 27, 2026 | ||
| Chart Understanding | ChartQA 1.0 (test) | 33 | Feb 27, 2026 | ||
| Latency Prediction | NNLQ in-domain v1 (test) | 33 | Feb 27, 2026 | ||
| Novel View Synthesis | nuScenes (val) | 33 | Mar 19, 2026 | ||
| Deep Research | BrowseComp | 33 | Mar 27, 2026 | ||
| Argument Component Detection & Classification | ElecDeb (test) | 33 | Feb 26, 2026 | ||
| Sequential Recommendation | LastFM | 33 | Jun 16, 2026 | ||
| Multi-task Adversarial Attack Evaluation | COCO, Flickr30k, TextVQA, VQAv2, POPE | 33 | Feb 26, 2026 | ||
| Visual Question Answering | TextVQA | 33 | Feb 26, 2026 | ||
| Recommendation | Electronics | 33 | Apr 27, 2026 | ||
| Hallucination Detection | RAGTruth RT-QA 1.0 (test) | 33 | Jun 8, 2026 | ||
| Offline Reinforcement Learning | D4RL MuJoCo walker2d-medium | 33 | Jun 11, 2026 | ||
| Offline Reinforcement Learning | D4RL MuJoCo halfcheetah-medium | 33 | Jun 11, 2026 | ||
| Class-conditional image generation | ImageNet-1K 512x512 (val) | 33 | Feb 26, 2026 | ||
| Face Forgery Detection | Celeb-DF v2 | 33 | Apr 16, 2026 | ||
| Node classification | Penn 94 | 33 | Apr 14, 2026 | ||
| Graph Out-of-Distribution Detection | AIDS DHFR ID OOD | 33 | Apr 1, 2026 | ||
| Graph Anomaly Detection | IMDB-B | 33 | May 27, 2026 | ||
| Graph Anomaly Detection | NCI1 | 33 | May 27, 2026 | ||
| Graph Anomaly Detection | COX2 | 33 | May 27, 2026 |