Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1758 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Response Quality Evaluation | MT-Bench | 19 | Feb 26, 2026 | ||
| Code Repair | HumanEvalFix (test) | 19 | Jun 4, 2026 | ||
| Code-to-text | HumanEvalExplain (test) | 19 | Feb 26, 2026 | ||
| WSI Report Generation | TCGA-based dataset (test) | 19 | Feb 26, 2026 | ||
| Question Answering | CondaQA (test) | 19 | Feb 26, 2026 | ||
| Multi-modal retrieval (Text to Text/Image-Text) | WebQA | 19 | Feb 26, 2026 | ||
| Text-to-Image Generation | MS-COCO 512x512 zero-shot | 19 | Feb 26, 2026 | ||
| Natural Language Understanding | GLUE & SuperGLUE (test) | 19 | Apr 21, 2026 | ||
| Product Rating | LaMP-3 1.0 (test) | 19 | Jun 4, 2026 | ||
| Movie Tagging | LaMP-2 Personalized Movie Tagging 1.0 (test) | 19 | Jun 4, 2026 | ||
| Machine Translation Evaluation | WMT MQM Segment-level 22 | 19 | Feb 26, 2026 | ||
| Machine Translation Evaluation | WMT MQM System-level 22 | 19 | Feb 26, 2026 | ||
| Image Reconstruction | COCO 5k 2017 (val) | 19 | Jun 30, 2026 | ||
| Event Coreference Resolution | ECB+ (test) | 19 | Feb 26, 2026 | ||
| Rotated Object Detection | DOTA 2.0 (test) | 19 | Feb 26, 2026 | ||
| Texture Classification | DTD (test) | 19 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | Near OOD datasets (Dnear) (test) | 19 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | D_near | 19 | Feb 26, 2026 | ||
| Science Question Answering | ScienceQA (val) | 19 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (test) | 19 | Feb 26, 2026 | ||
| Multimodal Understanding | MMBench v1.1 (test) | 19 | Feb 26, 2026 | ||
| Image Deraining | Rain100L | 19 | Feb 26, 2026 | ||
| Knowledge Graph Reasoning | WN18RR | 19 | Feb 26, 2026 | ||
| Knowledge Graph Reasoning | Kinship (test) | 19 | Feb 26, 2026 | ||
| RGB-T Tracking | GTOT (test) | 19 | Feb 26, 2026 |