Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2377 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Test-Time Personalization | Truthful QA | 15 | Jun 2, 2026 | ||
| Test-Time Personalization | HelpSteer | 15 | Jun 2, 2026 | ||
| Mathematics | MATH500 | 15 | Jun 30, 2026 | ||
| Image Generation | GenEval | 15 | Jun 30, 2026 | ||
| Depression Detection | Mumtaz 2016 (10-fold cross-validation) | 15 | Jun 2, 2026 | ||
| Emotional Text-to-Speech | IEMOCAP | 15 | Jun 2, 2026 | ||
| Emotional Text-to-Speech | CREMA-D | 15 | Jun 2, 2026 | ||
| Table Question Answering | TQA-Bench | 15 | Jun 30, 2026 | ||
| Visual Question Answering | HoraVQA (curated) | 15 | Jun 1, 2026 | ||
| Web Navigation | 15 | Jun 1, 2026 | |||
| Web Navigation | Classifieds | 15 | Jun 1, 2026 | ||
| Truthfulness | TruthfulQA MC2 | 15 | Jun 8, 2026 | ||
| Equation-to-Visual Generation | E2V-Bench (test) | 15 | Jun 1, 2026 | ||
| Shift Detection | EuroSAT-C Far shift | 15 | Jun 1, 2026 | ||
| Shift Detection | EuroSAT-D Near shift | 15 | Jun 1, 2026 | ||
| Causal Discovery | Synthetic Data Observation-only (1000 samples) | 15 | Jun 1, 2026 | ||
| Causal Discovery | Semantic Causal Environment observation-only | 15 | Jun 1, 2026 | ||
| Long Video Understanding | LongVideoBench 2024 (val) | 15 | Jun 1, 2026 | ||
| Long Video Understanding | MLVU 2024 (test) | 15 | Jun 1, 2026 | ||
| Code Generation | LiveCodeBench (LCB) v5 (2410–2501) and v6 (2501–2504) | 15 | Jun 1, 2026 | ||
| Multi-hop Question Answering | GraphRAG-Bench | 15 | Jun 4, 2026 | ||
| Embedding Evaluation | MTEB Corrupt | 15 | Jun 1, 2026 | ||
| Embedding Evaluation | MTEB Clean | 15 | Jun 1, 2026 | ||
| Image-Text Retrieval | COCO (1K) | 15 | Jun 1, 2026 | ||
| Image Representation | ImageNet-1K 256x256 | 15 | Jun 1, 2026 |