Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1256 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | Combined Classification Suite Average | 24 | Feb 26, 2026 | ||
| Biomedical Image Classification | OpenSRH 1.0 (test) | 24 | Feb 26, 2026 | ||
| Video Understanding | MLVU (dev) | 24 | Jun 9, 2026 | ||
| Video Compression | 1920 x 1080 videos | 24 | Feb 26, 2026 | ||
| Video Recognition | Something-Something V2 | 24 | Jun 25, 2026 | ||
| Survival Prediction | TCGA-STAD (test) | 24 | Feb 26, 2026 | ||
| Multitask Language Understanding | MMLU | 24 | Feb 26, 2026 | ||
| Drug trafficking detection | Twitter-HetDrug 40% label setting (train) | 24 | Feb 26, 2026 | ||
| Drug trafficking detection | Twitter-HetDrug 20% label setting (train) | 24 | Feb 26, 2026 | ||
| Drug trafficking detection | Twitter-HetDrug 10% label setting (train) | 24 | Feb 26, 2026 | ||
| Anomaly Detection | BrainMRI | 24 | Feb 26, 2026 | ||
| Workflow Extraction | SynthABCD | 24 | Feb 26, 2026 | ||
| Workflow Extraction | ABCD | 24 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | walker2d Mixed Dataset | 24 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | hopper Mixed Dataset | 24 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | halfcheetah Mixed Dataset | 24 | Feb 26, 2026 | ||
| Domain Adaptation | ImageNet Domain Adaptation | 24 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 VTAB-1K | 24 | Feb 26, 2026 | ||
| Explanation Faithfulness | Emotion | 24 | Feb 26, 2026 | ||
| Explanation Faithfulness | SNLI | 24 | Feb 26, 2026 | ||
| Explanation Faithfulness | Med-BIOS | 24 | Feb 26, 2026 | ||
| Explanation Faithfulness | SST-2 | 24 | Feb 26, 2026 | ||
| Video Compression | UVG standard (full) | 24 | Feb 26, 2026 | ||
| Anomaly detection | 24 | May 27, 2026 | |||
| Context-faithful Question Answering | ConFiQA | 24 | Feb 26, 2026 |