Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 810 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Action Recognition | Something-Something V2 | 31 | Mar 19, 2026 | ||
| Image Classification | ImageNet-C | 31 | Jul 2, 2026 | ||
| ECG Classification | PTBXL Sub | 31 | Jun 23, 2026 | ||
| Spatial Reasoning | VSI-Bench (test) | 31 | May 11, 2026 | ||
| Few-Shot Image Classification | FGVC Aircraft (test) | 31 | Feb 26, 2026 | ||
| Long-context Input (Summarization) | GovReport | 31 | May 20, 2026 | ||
| Node Classification | Cora (ID) | 31 | Mar 10, 2026 | ||
| Multi-Agent Path Finding (MAPF) | warehouse 161x63 | 31 | Feb 26, 2026 | ||
| Time Series Anomaly Detection | PSM (test) | 31 | May 12, 2026 | ||
| Time Series Anomaly Detection | SWaT (test) | 31 | May 12, 2026 | ||
| Time Series Anomaly Detection | SMAP (test) | 31 | May 12, 2026 | ||
| Time Series Anomaly Detection | SWAN | 31 | May 12, 2026 | ||
| Visual Question Answering | GQA v1.0 (test) | 31 | Mar 24, 2026 | ||
| Image Quality Assessment | LIVE original (test) | 31 | Feb 26, 2026 | ||
| Multi-task Language Understanding | MMLU | 31 | Feb 26, 2026 | ||
| Zero-shot Classification | WinoGrande, PiQA, HellaSwag, ARC-easy, ARC-challenge, BoolQ Zero-shot | 31 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 standard (test) | 31 | Feb 26, 2026 | ||
| Image Classification | SVHN (test) | 31 | Feb 26, 2026 | ||
| Multimodal mathematical reasoning | MathVision | 31 | May 22, 2026 | ||
| Multi-label classification | COCO 2014 (test) | 31 | Feb 26, 2026 | ||
| Multistep Reasoning | MUSR | 31 | Apr 9, 2026 | ||
| Hallucination Mitigation | KG-FPQ | 31 | Feb 26, 2026 | ||
| Semantic Alignment | Parachute | 31 | Feb 26, 2026 | ||
| Semantic Alignment | Van Gogh | 31 | Feb 26, 2026 | ||
| Semantic Alignment | Nudity-I2P | 31 | Feb 26, 2026 |