Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 82 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Instance Segmentation | ScanNet v2 (test) | 135 | Feb 26, 2026 | ||
| Named Entity Recognition | CoNLL English 2003 (test) | 135 | Feb 26, 2026 | ||
| Image Classification | Flowers | 135 | May 18, 2026 | ||
| Multimodal Named Entity Recognition | Twitter-GMNER | 135 | Mar 19, 2026 | ||
| Hallucination Detection | HaluEval | 135 | Jun 19, 2026 | ||
| Continual Learning | TRACE | 135 | Jun 29, 2026 | ||
| Hallucination Detection | CoQA | 134 | Jun 12, 2026 | ||
| Science Question Answering | SciQ | 134 | Jun 18, 2026 | ||
| Image Classification | Tiny-ImageNet | 134 | Jun 11, 2026 | ||
| Real-time Visual Understanding | StreamingBench | 134 | Apr 30, 2026 | ||
| Mathematical reasoning | MATH 500 | 134 | Jun 30, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 134 | Jun 18, 2026 | ||
| Emotion Recognition | SEED-IV Session 1 → Session 2 | 134 | Feb 26, 2026 | ||
| OOD Detection | ImageNet 1k (test) | 134 | Jun 30, 2026 | ||
| Image Classification | SUN397, Cars, RESISC45, EuroSAT, SVHN, GTSRB, MNIST, DTD (test) | 134 | Jun 30, 2026 | ||
| Medical Question Answering | MedMCQA (test) | 134 | Feb 26, 2026 | ||
| Node classification | Minesweeper (test) | 134 | May 27, 2026 | ||
| Language Modeling | Lambada OpenAI | 134 | Jun 12, 2026 | ||
| Node Classification | Cora Synthetic (test) | 134 | Feb 26, 2026 | ||
| Deepfake Detection | CelebDF v2 | 134 | Jun 2, 2026 | ||
| Anomaly Detection | MVTec 3D-AD 1.0 (test) | 134 | Apr 28, 2026 | ||
| Medical Image Segmentation | GlaS | 134 | Jul 2, 2026 | ||
| Image Classification | ImageNet-C | 134 | Apr 21, 2026 | ||
| Text-to-Video Retrieval | VATEX | 134 | May 27, 2026 | ||
| Open Question Answering | Natural Questions (NQ) (test) | 134 | Feb 26, 2026 |