Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2021 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Similarity | BQ syntactically perturbed | 17 | Apr 2, 2026 | ||
| Text Classification | THUCNews syntactically perturbed | 17 | Apr 2, 2026 | ||
| Sentiment Analysis | Amazon syntactically perturbed | 17 | Apr 2, 2026 | ||
| Semantic Similarity | AFQMC syntactically perturbed | 17 | Apr 2, 2026 | ||
| Poetry Matching | CCPM | 17 | Apr 2, 2026 | ||
| Semantic Similarity | LCQMC | 17 | Apr 2, 2026 | ||
| Relation Extraction | FinRE | 17 | Apr 2, 2026 | ||
| Natural Language Inference | OCNLI | 17 | Apr 2, 2026 | ||
| Text Classification | TNews | 17 | Apr 2, 2026 | ||
| Reading Comprehension | DRCD | 17 | Apr 2, 2026 | ||
| Sentiment Analysis | ChnSent | 17 | Apr 2, 2026 | ||
| Image Classification | CUB (in-distrib.) | 17 | Jun 26, 2026 | ||
| Science Question Answering | ARC Challenge | 17 | Jun 1, 2026 | ||
| Attribution Topography Evaluation | PASCAL VOC 2012 (250 samples) | 17 | Apr 1, 2026 | ||
| Survival Analysis | NWTCO | 17 | May 25, 2026 | ||
| Image Classification | Food101 | 17 | May 18, 2026 | ||
| Extreme weather forecasting | WEATHER-5K 2023 (test) | 17 | Apr 1, 2026 | ||
| Global Station Weather Forecasting | WEATHER-5K | 17 | Apr 1, 2026 | ||
| Visual Relocalization | Cambridge Landmarks (test) | 17 | Apr 1, 2026 | ||
| Graph Coarsening | Citeseer | 17 | May 14, 2026 | ||
| Speech Separation | WSJ0 3mix | 17 | Apr 1, 2026 | ||
| Knowledge Graph Question Answering | GTSQA Ground-truth seed nodes WikiKG2 (test) | 17 | Apr 1, 2026 | ||
| Question Answering | GPQA | 17 | Jun 9, 2026 | ||
| Continual Learning | MLLM-CL Ability | 17 | Mar 31, 2026 | ||
| Domain-Incremental Learning | MLLM-CL Domain | 17 | Mar 31, 2026 |