Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 573 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Long Video Understanding | EgoSchema (val) | 39 | Jul 3, 2026 | ||
| Node Classification | AmzComp | 39 | Jun 4, 2026 | ||
| Open-vocabulary semantic segmentation | Pascal VOC 21 (With Background) | 39 | May 13, 2026 | ||
| Embodied Visual Question Answering | ERQA | 39 | Jun 11, 2026 | ||
| Real-world Visual Understanding | RealWorldQA | 39 | May 21, 2026 | ||
| Diagnostic Classification | EBRAINS | 39 | Mar 23, 2026 | ||
| Diagnostic Classification | Camelyon16 | 39 | Mar 23, 2026 | ||
| Diagnostic Classification | BRACS | 39 | Mar 23, 2026 | ||
| Randomness Testing | Linear PRNG sequences | 39 | Mar 23, 2026 | ||
| Classification | MetaShift | 39 | Jun 4, 2026 | ||
| Mathematical Reasoning | MATH | 39 | Jun 2, 2026 | ||
| General Language Understanding | MMLU | 39 | Apr 20, 2026 | ||
| Diagram Understanding | AI2D | 39 | May 8, 2026 | ||
| Exemplar-Free Class-Incremental Learning | CIFAR-100 Big start | 39 | Mar 20, 2026 | ||
| Complex Reasoning | Video-TT | 39 | Jun 23, 2026 | ||
| Image Classification | DTD | 39 | May 26, 2026 | ||
| Trajectory Prediction | Argoverse 1.1 (val) | 39 | Mar 19, 2026 | ||
| Video Reasoning | VBVR-Bench Out-of-Domain | 39 | Jun 2, 2026 | ||
| Node Classification | Computers Random (test) | 39 | Mar 18, 2026 | ||
| End-to-End Autonomous Driving | Bench2Drive 220 routes official | 39 | Jun 5, 2026 | ||
| Category Discovery | CIFAR-100 | 39 | May 1, 2026 | ||
| Long-context language model evaluation | HELMET | 39 | Apr 13, 2026 | ||
| Object Detection | M4-SAR | 39 | Mar 11, 2026 | ||
| Reasoning | GPQA (80% test) | 39 | Mar 10, 2026 | ||
| Safety Evaluation | HarmBench | 39 | Jun 5, 2026 |