Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1453 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | ImageNet-1k | 21 | Apr 16, 2026 | ||
| Visual Storytelling | ViStoryBench Lite 2025 | 21 | Apr 16, 2026 | ||
| Video Quality Assessment | Human-AGVQA | 21 | Apr 15, 2026 | ||
| Video Quality Assessment | T2VQA | 21 | Apr 15, 2026 | ||
| Regression | RelBench v2 (test) | 21 | Jul 8, 2026 | ||
| Fake Image Detection | GAN-trained Generalization Evaluation Suite (test) | 21 | Apr 15, 2026 | ||
| Fraud Detection | Ethereum | 21 | Apr 15, 2026 | ||
| Spreadsheet Understanding and Manipulation | SpreadsheetBench Hard Restriction | 21 | Apr 15, 2026 | ||
| Text Generation | Spec-Bench Overall | 21 | Apr 15, 2026 | ||
| Translation | Spec-Bench Trans. | 21 | Apr 15, 2026 | ||
| Summarization | Spec-Bench Sum. | 21 | Apr 15, 2026 | ||
| Retrieval-Augmented Generation | Spec-Bench RAG | 21 | Apr 15, 2026 | ||
| Question Answering | Spec-Bench QA | 21 | Apr 15, 2026 | ||
| Multi-turn Dialogue | Spec-Bench Multi. | 21 | Apr 15, 2026 | ||
| Mathematical Reasoning | Spec-Bench Math | 21 | Apr 15, 2026 | ||
| Near-OOD detection | Average (CIFAR-10, CIFAR-100, ImageNet-200) | 21 | Apr 15, 2026 | ||
| Far-OOD Detection | Average (CIFAR-10, CIFAR-100, ImageNet-200) | 21 | Apr 15, 2026 | ||
| Far-OOD Detection | ImageNet 200 | 21 | Apr 15, 2026 | ||
| Face Forgery Detection | DiFF Cross Avg | 21 | Apr 14, 2026 | ||
| Image Denoising | CAVE Case 1 | 21 | Apr 14, 2026 | ||
| Intra-instance detection | CZII | 21 | Apr 14, 2026 | ||
| Intra-instance detection | EMPIAR-10499 (test) | 21 | Apr 14, 2026 | ||
| Intra-instance detection | EMPIAR-10304 | 21 | Apr 14, 2026 | ||
| Interclass Confusion Unlearning | CIFAR-100 | 21 | Apr 14, 2026 | ||
| Poisoning Unlearning | CIFAR-100 | 21 | Apr 14, 2026 |