Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1223 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Cultural Alignment | GlobalOpinionQA | 24 | Jun 18, 2026 | ||
| Cultural Alignment | Prism | 24 | Mar 9, 2026 | ||
| Cultural Alignment | CulturalBench Hard | 24 | Mar 9, 2026 | ||
| Cultural Alignment | CulturalBench Easy | 24 | Mar 9, 2026 | ||
| Image Super-Resolution | Manga109 x4 | 24 | May 19, 2026 | ||
| Molecular Classification | Molecular Classification | 24 | Mar 6, 2026 | ||
| Morphological Classification | Morphological Classification | 24 | Mar 6, 2026 | ||
| Molecular Classification | 33-task benchmark Molecular Classification | 24 | Mar 6, 2026 | ||
| Morphological Classification | 33-task benchmark Morphological Classification | 24 | Mar 6, 2026 | ||
| Single-Object Tracking | DiDi | 24 | Mar 6, 2026 | ||
| Multi-hop Question Answering | HotpotQA | 24 | Mar 6, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 24 | Mar 6, 2026 | ||
| Mathematical Reasoning | AMC | 24 | Mar 6, 2026 | ||
| Causal Discovery | Simulated datasets | 24 | Mar 6, 2026 | ||
| Node Classification | Pubmed | 24 | Mar 6, 2026 | ||
| Node Classification | Cora | 24 | Mar 6, 2026 | ||
| Specific Provision Prediction | LeCaRD v2 | 24 | May 27, 2026 | ||
| General Provision Prediction | LeCaRD v2 | 24 | May 27, 2026 | ||
| Gaze Estimation | GFIE trained on Gaze360 (Backward) | 24 | Mar 6, 2026 | ||
| Language Modeling | WikiText-2 context length 2048 (val) | 24 | Mar 6, 2026 | ||
| 3D Medical Image Segmentation | MMWHS MRI | 24 | Mar 5, 2026 | ||
| 3D Medical Image Segmentation | MMWHS CT | 24 | Mar 5, 2026 | ||
| 3D Medical Image Segmentation | LIDC | 24 | Mar 5, 2026 | ||
| Semantic Segmentation | DSEC-Semantic v1 (test) | 24 | Mar 5, 2026 | ||
| Semantic Segmentation | DDD17-Seg v1 (test) | 24 | Mar 5, 2026 |