Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1197 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Scene Graph Generation | VG 150 (test) | 24 | Apr 27, 2026 | ||
| Explanation Sparsity | CUB | 24 | Apr 27, 2026 | ||
| Explanation Sparsity | ImageNet | 24 | Apr 27, 2026 | ||
| Attribution Faithfulness | CUB | 24 | Apr 27, 2026 | ||
| Feature Attribution | CUB | 24 | Apr 27, 2026 | ||
| Feature Attribution | ImageNet | 24 | Apr 27, 2026 | ||
| Open-domain Question Answering | Bamboogle out-of-domain | 24 | Apr 27, 2026 | ||
| Machine Translation (X→En) | Multilingual Intersection Low Resource | 24 | Apr 27, 2026 | ||
| Machine Translation (En→X) | Multilingual Intersection Low Resource | 24 | Apr 27, 2026 | ||
| Machine Translation (X→Zh) | Multilingual Intersection Medium Resource | 24 | Apr 27, 2026 | ||
| Machine Translation (Zh→X) | Multilingual Intersection Medium Resource | 24 | Apr 27, 2026 | ||
| Machine Translation (X→Zh) | Multilingual Intersection High Resource | 24 | Apr 27, 2026 | ||
| Machine Translation (Zh→X) | Multilingual Intersection High Resource | 24 | Apr 27, 2026 | ||
| Machine Translation | FLORES Low Resource | 24 | Apr 27, 2026 | ||
| Inference Efficiency and Reasoning | Nine Datasets (Aggregate) | 24 | Apr 27, 2026 | ||
| Jailbreak Discovery | Jailbreak Discovery Evaluation Set (test) | 24 | Apr 27, 2026 | ||
| Identity Matching | Identity Matching Dataset | 24 | Apr 24, 2026 | ||
| Machine-generated code detection | SemEval Task 13 Subtask A 2026 official (test) | 24 | Jun 25, 2026 | ||
| Anomaly Detection | Multimodal smart grid dataset 0% noise (test) | 24 | Apr 24, 2026 | ||
| Early Anomaly Detection | PSML multimodal dataset 10% noise (test) | 24 | Apr 24, 2026 | ||
| Embodied Task Planning | VirtualHome | 24 | May 19, 2026 | ||
| Unsafe content generation | Internal Safety Collapse (ISC) | 24 | Apr 24, 2026 | ||
| Reasoning | superGPQA | 24 | Apr 23, 2026 | ||
| Multilingual Language Understanding | MMLU-ProX (test) | 24 | Apr 23, 2026 | ||
| Object Hallucination Evaluation | OPOPE MSCOCO (test) | 24 | Apr 23, 2026 |