Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2662 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Average Dose-Response Function (ADRF) Estimation | sinusoidal (p=0.25, n=800) synthetic (test) | 14 | May 4, 2026 | ||
| Average Dose-Response Function (ADRF) Estimation | parabola p=0.25, n=800 synthetic (test) | 14 | May 4, 2026 | ||
| Multi-label classification | PASCAL VOC 2012 (val) | 14 | May 1, 2026 | ||
| Question Answering | 2WikiMHQA (test) | 14 | May 1, 2026 | ||
| Math Reasoning | MATH (test) | 14 | May 1, 2026 | ||
| Action Recognition | BABEL 100% OR | 14 | May 1, 2026 | ||
| Human Preference Prediction | internal benchmark | 14 | May 1, 2026 | ||
| Image Classification | PACS Art | 14 | May 1, 2026 | ||
| Text Reasoning | Minerva Math | 14 | May 1, 2026 | ||
| Text Reasoning | HMMT 2025 | 14 | May 1, 2026 | ||
| Text Reasoning | AIME 2024 | 14 | May 1, 2026 | ||
| Image Reasoning | ZeroBench sub | 14 | May 1, 2026 | ||
| Image Reasoning | MMMU-Pro | 14 | May 1, 2026 | ||
| Streaming Image Classification | EMNIST label-permuted 5M interactions 2000 tasks (streaming) | 14 | May 1, 2026 | ||
| Image Classification | MNIST Rotated | 14 | Jun 25, 2026 | ||
| Synthetic generation under constraints | Box | 14 | May 1, 2026 | ||
| Text-to-Image Generation | DrawBench | 14 | Apr 30, 2026 | ||
| Monocular Depth Estimation | Argoverse | 14 | Jun 16, 2026 | ||
| Instruction-based Image Editing | ImgEdit-Bench | 14 | Jun 11, 2026 | ||
| Multimodal Recommendation | Amazon Software | 14 | Apr 30, 2026 | ||
| Multimodal Recommendation | Amazon Game | 14 | Apr 30, 2026 | ||
| Multimodal Recommendation | Amazon CD | 14 | Apr 30, 2026 | ||
| Multimodal Recommendation | Industry | 14 | Apr 30, 2026 | ||
| Malicious Package Detection | QUT-DV25 (test) | 14 | Apr 30, 2026 | ||
| Medical Image Classification | BrEaST (test) | 14 | Jun 2, 2026 |