Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1439 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Aspect-Based Sentiment Analysis | Restaurant 14 | 21 | May 22, 2026 | ||
| Speaker-Independent Keyword Spotting | LibriPhrase Hard | 21 | May 22, 2026 | ||
| Adversarial Attack | CIFAR-10 | 21 | May 22, 2026 | ||
| Image content search | Synthetic 2048 x 2048 instances | 21 | May 22, 2026 | ||
| Mathematical Reasoning | HMMT25 | 21 | May 21, 2026 | ||
| Temporal scRNA-seq Modeling under Sparsity | DR (Drosophila) Hard Sparse Modeling | 21 | May 21, 2026 | ||
| Temporal scRNA-seq Extrapolation | DR (Drosophila) Medium (Extrapolation) | 21 | May 21, 2026 | ||
| Temporal scRNA-seq Interpolation | DR (Drosophila) Easy (Interpolation) | 21 | May 21, 2026 | ||
| Financial Trading | Dow Jones 30 (test) | 21 | May 21, 2026 | ||
| Visual Question Answering | ScienceQA SQA-IMG | 21 | Jun 18, 2026 | ||
| Multi-task Language Understanding | MMLU | 21 | May 21, 2026 | ||
| Reconstruction | WED 256x256 (test) | 21 | May 21, 2026 | ||
| Estimated Time of Arrival | Porto | 21 | Jul 1, 2026 | ||
| Explicit-Implicit Reasoning | MixRea | 21 | May 20, 2026 | ||
| Referring Video Object Segmentation | Ref-YTVOS | 21 | May 20, 2026 | ||
| Multi-modal Document Understanding | OCRBench | 21 | May 20, 2026 | ||
| Illuminant Estimation | NUS-8 (test) | 21 | May 20, 2026 | ||
| Illuminant Estimation | Gehler-Shi (test) | 21 | May 20, 2026 | ||
| Object Detection | Insulator fault detection dataset | 21 | May 20, 2026 | ||
| Jailbreak Attack | AdvBench | 21 | May 20, 2026 | ||
| Scientific Question Answering | GPQA | 21 | May 20, 2026 | ||
| Instruction Following | IFEval | 21 | May 20, 2026 | ||
| Mathematical Reasoning | MATH 500 | 21 | May 20, 2026 | ||
| Mathematical Reasoning | AIME 25 | 21 | May 20, 2026 | ||
| Mathematical Reasoning | AIME24 | 21 | May 20, 2026 |