Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1940 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video Referring Expression Segmentation | MeViS (val-u) | 18 | Feb 26, 2026 | ||
| Online Test-Time Adaptation | 11 VLM Downstream Datasets (ImageNet, SUN397, FGVC-Aircraft, EuroSAT, Stanford Cars, Food-101, Oxford-IIIT Pets, Oxford Flowers 102, Caltech-101, DTD, UCF-101) v1 (test) | 18 | Feb 26, 2026 | ||
| H2 Assessment | HONEST | 18 | Feb 26, 2026 | ||
| Multi-View Pose Estimation | ScanNet supervised (test) | 18 | Feb 26, 2026 | ||
| Summarization | CNN | 18 | Feb 26, 2026 | ||
| Clock Reading | COCO, OpenImages, and Clock Movies Averaged (test) | 18 | Feb 26, 2026 | ||
| Knowledge-based Visual Question Answering | OKVQA (test) | 18 | Jun 15, 2026 | ||
| Causal Discovery | MECD (test) | 18 | Feb 26, 2026 | ||
| Tabular Classification | NUM (L) (test) | 18 | Feb 26, 2026 | ||
| Agent Task Performance | AgentDojo Banking | 18 | Feb 26, 2026 | ||
| Robot Manipulation | CALVIN ABC->D 1.0 | 18 | Feb 26, 2026 | ||
| Action Recognition | NTU-60 (x-view) | 18 | Mar 12, 2026 | ||
| Image Semantic Editing | PIE-Bench (test) | 18 | Feb 26, 2026 | ||
| Prompt Harmfulness Classification | WILDGUARD (test) | 18 | May 29, 2026 | ||
| Safety Moderation | WILDJAILBREAK (val) | 18 | Feb 26, 2026 | ||
| Verification | Simulation Distribution Shift (test) | 18 | Feb 26, 2026 | ||
| Verification | Simulation In Distribution (test) | 18 | Feb 26, 2026 | ||
| Node Classification | Chameleon Dense Filtered | 18 | Feb 26, 2026 | ||
| Language Identification | ML-SUPERB 10-min Normal | 18 | Feb 26, 2026 | ||
| Boolean Question Answering | BoolQ | 18 | Feb 26, 2026 | ||
| Abstractive Summarization | MeetingBank (test) | 18 | Feb 26, 2026 | ||
| Camera pose estimation | TUM-dynamics (test) | 18 | Jun 30, 2026 | ||
| Text-to-Image Personalization | DreamBooth original (test) | 18 | Feb 26, 2026 | ||
| link prediction | Texas | 18 | May 12, 2026 | ||
| Private Transformer Inference Efficiency | Transformer Block BERT-base settings | 18 | Feb 26, 2026 |