Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1339 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Phone recognition | TIMIT (test) | 23 | Jun 16, 2026 | ||
| Image Clustering | FRGC | 23 | Feb 26, 2026 | ||
| de novo molecular design | GuacaMol goal-directed tasks | 23 | Feb 26, 2026 | ||
| Description-guided molecule design | Mol-Instructions | 23 | Jun 9, 2026 | ||
| Locomotion Control | D4RL Walker2d medium-expert | 23 | Feb 26, 2026 | ||
| Semi-supervised Image Classification | CIFAR100 (test) | 23 | Feb 26, 2026 | ||
| 20-way 5-shot Classification | Omniglot (test) | 23 | Feb 26, 2026 | ||
| Dynamical systems reconstruction | Lorenz-63 3d | 23 | Feb 26, 2026 | ||
| Crystal Property Prediction | JARVIS (test) | 23 | Jun 4, 2026 | ||
| 3D shape recognition | ModelNet10 | 23 | Feb 26, 2026 | ||
| Classification | GTZAN (test) | 23 | Feb 26, 2026 | ||
| Video Quality Assessment | YouTube-UGC 1080p | 23 | Feb 26, 2026 | ||
| Image Generation | ImageNet-32 | 23 | May 13, 2026 | ||
| Multimodal Understanding | MM-Vet v2 | 23 | Apr 3, 2026 | ||
| Visual Reasoning and Instruction Following | MM-Vet | 23 | Feb 26, 2026 | ||
| Person Re-Identification | CUHK03 NP Market1501 (test) | 23 | Feb 26, 2026 | ||
| Hallucination Evaluation | CRPE relation | 23 | Feb 27, 2026 | ||
| Multi-image Understanding | MMT-Bench (val) | 23 | Feb 27, 2026 | ||
| Multi-image Understanding | BLINK (val) | 23 | Feb 27, 2026 | ||
| Medical Image Classification | BUSI (test) | 23 | Jul 7, 2026 | ||
| Medical Image Segmentation | DDTI | 23 | Jun 23, 2026 | ||
| Topic Modeling | DBLP | 23 | Apr 1, 2026 | ||
| Topic Modeling | M10 | 23 | Apr 1, 2026 | ||
| Moment Retrieval | TACOS (test) | 23 | Feb 26, 2026 | ||
| Categorical Emotion Recognition | MAFW 11-class | 23 | Feb 26, 2026 |