Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 494 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-task Language Understanding | MMLU-PRO | 42 | Jul 3, 2026 | ||
| Scientific Reasoning | GPQA | 42 | Jul 3, 2026 | ||
| Reasoning | BBH | 42 | Jul 3, 2026 | ||
| Leakage Detection | APPS | 42 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10 (test) | 42 | Jun 30, 2026 | ||
| Image Classification | CIFAR-100 (test) | 42 | Jun 30, 2026 | ||
| Machine Translation | Conversational (test) | 42 | Jun 30, 2026 | ||
| Provenance Tracing | MS-COCO | 42 | Jun 30, 2026 | ||
| Provenance Tracing | LAION | 42 | Jun 30, 2026 | ||
| Provenance Tracing | ImageNet | 42 | Jun 30, 2026 | ||
| Segmentation localization | Contrast agent CT dataset | 42 | Jun 30, 2026 | ||
| Fidelity evaluation | Contrast agent application | 42 | Jun 30, 2026 | ||
| Image Classification | DomainNet fine-grained | 42 | Jun 30, 2026 | ||
| Image Classification | Tiny-ImageNet fine-grained | 42 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10 fine-grained | 42 | Jun 30, 2026 | ||
| Image Classification | DomainNet fine-grained (test) | 42 | Jun 30, 2026 | ||
| Image Classification | Tiny-ImageNet fine-grained (test) | 42 | Jun 30, 2026 | ||
| Image Classification | CIFAR-100 fine-grained (test) | 42 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10 fine-grained (test) | 42 | Jun 30, 2026 | ||
| Untargeted Reconstruction Attack | ChatDoctor 250 adversarial prompts | 42 | Jun 24, 2026 | ||
| Text generation | DFM 1024 samples masked backbone | 42 | Jun 24, 2026 | ||
| Image Generation | WISE legacy (test) | 42 | Jun 23, 2026 | ||
| Training Efficiency Profiling | Qwen3 family S=1024 (train profiling) | 42 | Jun 23, 2026 | ||
| Question Answering | CMB Exam | 42 | Jun 23, 2026 | ||
| Question Answering | MedQA | 42 | Jun 23, 2026 |