Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1449 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Time Series Classification | UCR Archive all datasets | 21 | Apr 29, 2026 | ||
| Tokenization Disambiguation | IMDB English | 21 | Apr 29, 2026 | ||
| Linguistic Steganography | Chinese IMDB | 21 | Apr 29, 2026 | ||
| Summarization | Summarization | 21 | Apr 29, 2026 | ||
| Math | Math | 21 | Apr 29, 2026 | ||
| Motion Deblurring | ImageNet-1K | 21 | Apr 29, 2026 | ||
| Gaussian Deblurring | ImageNet-1K | 21 | Apr 29, 2026 | ||
| Box Inpainting | ImageNet-1K | 21 | Apr 29, 2026 | ||
| Random Inpainting | ImageNet 1K | 21 | Apr 29, 2026 | ||
| Super Resolution (SR x4) | ImageNet-1K | 21 | Apr 29, 2026 | ||
| Question Answering | RESTOR | 21 | Apr 29, 2026 | ||
| General & Complex QA | VMME | 21 | Apr 28, 2026 | ||
| Image Classification | MNIST (test) | 21 | Apr 28, 2026 | ||
| Text-to-SQL | Spider Snow 2.0 (test) | 21 | Jun 5, 2026 | ||
| Cross-domain object insertion | AIComposer | 21 | Jun 2, 2026 | ||
| Recommendation | Ciao | 21 | Apr 27, 2026 | ||
| Scholarly Title Generation | LaMP Scholarly Title Generation | 21 | May 12, 2026 | ||
| Offline Reinforcement Learning | D4RL adroit 12 tasks | 21 | Jun 2, 2026 | ||
| Offline Reinforcement Learning | D4RL antmaze 6 tasks | 21 | Jun 2, 2026 | ||
| Machine Unlearning | TOFU 20% known forget set (DFk) | 21 | Apr 27, 2026 | ||
| Machine Unlearning | Enron + News (20% forget set) | 21 | Apr 27, 2026 | ||
| Pedestrian Trajectory Prediction | PSI | 21 | Apr 27, 2026 | ||
| Machine Translation (X→Zh) | Multilingual Intersection Low Resource | 21 | Apr 27, 2026 | ||
| Machine Translation (Zh→X) | Multilingual Intersection Low Resource | 21 | Apr 27, 2026 | ||
| Reasoning | Reasoning Benchmarks GPQA-Diamond AIME2024 MATH500 HumanEval | 21 | Apr 27, 2026 |