Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1982 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Question Answering | OK-VQA | 18 | Feb 26, 2026 | ||
| Echocardiography Video Segmentation and Ejection Fraction Estimation | CAMUS | 18 | Feb 26, 2026 | ||
| Factuality Evaluation | FACTOR | 18 | Feb 26, 2026 | ||
| Zero-shot Natural Language Understanding | Standard Zero-shot NLU Suite (ARC-challenge, ARC-easy, BoolQ, HellaSwag, LAMBADA, PIQA, RACE, SciQ, Record, OBQA) | 18 | Feb 26, 2026 | ||
| Medical Image Classification | ChestX-ray14 | 18 | Feb 26, 2026 | ||
| Part Segmentation | Pascal-Part-116 (test) | 18 | Feb 26, 2026 | ||
| Summarization | SuperSummary (test) | 18 | Feb 26, 2026 | ||
| Summarization | Multi-LexSum (test) | 18 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 instance-dependent noise (IDN) (test) | 18 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 instance-dependent noise (IDN) (test) | 18 | Feb 26, 2026 | ||
| Embedding Space Analysis | OpenWebText | 18 | Feb 26, 2026 | ||
| Dichotomous Image Segmentation | DIS5K (val) | 18 | May 15, 2026 | ||
| Lesion Segmentation | BL | 18 | Feb 26, 2026 | ||
| Lesion Segmentation | LI | 18 | Feb 26, 2026 | ||
| Lesion Segmentation | CP | 18 | Feb 26, 2026 | ||
| Lesion Segmentation | ADC | 18 | Feb 26, 2026 | ||
| Lesion Segmentation | BT | 18 | Feb 26, 2026 | ||
| Lesion Segmentation | WA | 18 | Feb 26, 2026 | ||
| Visual Localization | Aachen Day-Night 1.0 (Night) | 18 | Feb 26, 2026 | ||
| Continual Anomaly Detection | VisA Setting 5: 11-1 with 1 Step | 18 | Jun 2, 2026 | ||
| Instruction Following | Vicuna | 18 | Feb 26, 2026 | ||
| Summarization | SamSum (test) | 18 | Feb 26, 2026 | ||
| NL2Code Search | CSN (CodeSearchNet) (test) | 18 | Feb 26, 2026 | ||
| Attribution | QuoteSum (test) | 18 | Feb 26, 2026 | ||
| Brain Disorder Classification | ADNI Tenfold cross-validation | 18 | Feb 26, 2026 |