Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1653 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Word Relation Prediction | Landmark-Continent | 20 | Feb 27, 2026 | ||
| Word Relation Prediction | Product-Company | 20 | Feb 27, 2026 | ||
| Word Relation Prediction | Person-Occupation | 20 | Feb 27, 2026 | ||
| Sentiment Analysis | 20 | Feb 26, 2026 | |||
| Grounded Generation | QAMPARI (test) | 20 | Feb 26, 2026 | ||
| Visual Perception | MMBench (P) | 20 | Feb 26, 2026 | ||
| Natural Language Generation and Understanding | S_NLG and S_NLU (test) | 20 | Feb 26, 2026 | ||
| Mental State Inference | MMToM-QA human 1.0 (test) | 20 | Feb 26, 2026 | ||
| Named Entity Recognition | Financial Named Entity Recognition | 20 | Jun 11, 2026 | ||
| Brain Tumor Segmentation | BraTS 2018 (online evaluation) | 20 | Feb 26, 2026 | ||
| Claim-level Uncertainty Quantification | FactScore English (test) | 20 | Feb 26, 2026 | ||
| Fact-checking of atomic claims | FactScore English | 20 | Feb 26, 2026 | ||
| Multi-modal Reasoning and Understanding | MM-Vet | 20 | Apr 14, 2026 | ||
| Anomaly Detection | SMAP | 20 | Feb 26, 2026 | ||
| Anomaly Detection | MSL | 20 | Feb 26, 2026 | ||
| Image Generation | ImageNet-1K 512x512 (val) | 20 | Mar 27, 2026 | ||
| Meme Intervention Generation | ICMM (test) | 20 | Feb 26, 2026 | ||
| Temporal Knowledge Graph Prediction | ICEWS05-15 (test) | 20 | Feb 26, 2026 | ||
| Domain-Incremental Learning | DomainNet 6T | 20 | Feb 26, 2026 | ||
| Data-Incremental Learning | ImageNet-100 (5T) | 20 | Feb 26, 2026 | ||
| Image Retrieval | IMAGECODE Video subset (test) | 20 | Feb 26, 2026 | ||
| Abstractive Summarization | XL-Sum (test) | 20 | Mar 19, 2026 | ||
| 2D Ephemeral Object Segmentation | Mapverse-Ithaca365 1.0 (test) | 20 | Feb 26, 2026 | ||
| Horizontal Object Detection | DIOR 1.0 (test) | 20 | Feb 26, 2026 | ||
| Question Answering | MMLU | 20 | Feb 26, 2026 |