Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1427 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Forgery localization | FKG-50K | 21 | Jun 24, 2026 | ||
| Text-to-Image Generation | MS-COCO Unseen Concepts | 21 | Jun 24, 2026 | ||
| File-level localization | SWE-Bench Verified | 21 | Jun 24, 2026 | ||
| Backdoor attack | CIFAR-10 | 21 | Jun 23, 2026 | ||
| Causal Fairness Regression | Synthetic Nonlinear v1 (test) | 21 | Jun 23, 2026 | ||
| Causal Fairness Regression | Synthetic Linear v1 (test) | 21 | Jun 23, 2026 | ||
| Mathematical Reasoning | In-Distribution AIME24 MATH-500 OlympiadBench Minerva | 21 | Jun 23, 2026 | ||
| Segmentation | Hecktor 2022 | 21 | Jun 23, 2026 | ||
| Segmentation | AutoPET-II | 21 | Jun 23, 2026 | ||
| Multi-Agent Pathfinding | Warehouse map | 21 | Jun 23, 2026 | ||
| Graph Alignment | Coauthor CS | 21 | Jun 23, 2026 | ||
| Image Classification | ImageNet LT | 21 | Jun 23, 2026 | ||
| Image Classification | CIFAR100 LT-10 | 21 | Jun 23, 2026 | ||
| Image Classification | CIFAR100 LT-100 | 21 | Jun 23, 2026 | ||
| Image Classification | CIFAR-10 LT-10 | 21 | Jun 23, 2026 | ||
| Action Classification | Smarthome CS | 21 | Jun 23, 2026 | ||
| Adversarial Attack Detection | ImageNet | 21 | Jun 23, 2026 | ||
| Zero-shot QA and Language Modeling | Wiki, BoolQ, RTE, ARC-C, TinyM | 21 | Jun 19, 2026 | ||
| Fingerprint Detectability | Fingerprint Evaluation Set | 21 | Jun 19, 2026 | ||
| Node-wise classification | Synthetic A-Ci curves (test) | 21 | Jun 19, 2026 | ||
| Time Series Anomaly Detection | PSM | 21 | Jun 23, 2026 | ||
| Mixed reasoning tasks | Mixed workload n = 450 | 21 | Jun 18, 2026 | ||
| Social reasoning | Social regime (n = 300) | 21 | Jun 18, 2026 | ||
| Closed-ended reasoning | Closed regime n = 300 | 21 | Jun 18, 2026 | ||
| Abductive Natural Language Inference | AlphaNLI n=300 per condition (test) | 21 | Jun 18, 2026 |