Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 433 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Active Learning Image Classification | CIFAR-100 | 46 | May 15, 2026 | ||
| Video Understanding | Video-MME w/o sub. | 46 | Jun 12, 2026 | ||
| Image Classification | ImageNet-Woof (test) | 46 | May 21, 2026 | ||
| Multi-domain Task-Incremental Learning | MTIL Order I 5-shot (test) | 46 | May 22, 2026 | ||
| Multi-Hop QA | Bamboogle | 46 | May 13, 2026 | ||
| Multimodal Anomaly Detection | Real-IAD-MVN 5-view 1.0 (full) | 46 | May 11, 2026 | ||
| Classification | LDLSS Dataset Collection Overall | 46 | May 6, 2026 | ||
| Classification | Liver Disorder (LDLSS) | 46 | May 6, 2026 | ||
| Classification | Monks-1 LDLSS | 46 | May 6, 2026 | ||
| Classification | Hayes-Roth LDLSS | 46 | May 6, 2026 | ||
| Classification | Glass LDLSS | 46 | May 6, 2026 | ||
| Classification | Pima Indian LDLSS | 46 | May 6, 2026 | ||
| Classification | Iris LDLSS | 46 | May 6, 2026 | ||
| Hyperspectral Image Classification | Pavia University (80% test) | 46 | Apr 30, 2026 | ||
| Alignment Faking Rate Measurement | SORRY-BENCH | 46 | Jun 2, 2026 | ||
| Polymer-Solvent Interaction Prediction | PolySolv (10-fold cross-validation) | 46 | Apr 20, 2026 | ||
| Factual question answering | TriviaQA | 46 | Jun 2, 2026 | ||
| Incorrect Reasoning Path Detection | DeepScaleR | 46 | Apr 14, 2026 | ||
| Incorrect Reasoning Path Detection | GSM8K | 46 | Apr 14, 2026 | ||
| Incorrect Reasoning Path Detection | MATH500 | 46 | Apr 14, 2026 | ||
| Semantic Segmentation | Average Overall | 46 | Apr 23, 2026 | ||
| Summarization | XSum | 46 | Apr 10, 2026 | ||
| Continual Learning | CIFAR-100 | 46 | May 12, 2026 | ||
| Fault Detection | TEP | 46 | Apr 8, 2026 | ||
| Multimodal Evaluation | MM-Vet v2 | 46 | May 15, 2026 |