Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2345 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Long-context Understanding | LongBench | 16 | Feb 26, 2026 | ||
| Science Question Answering | GPQA | 16 | Feb 26, 2026 | ||
| Multi-task Language Understanding | MMLU-pro | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH | 16 | Feb 26, 2026 | ||
| Horizontal Object Detection | DIOR | 16 | Feb 26, 2026 | ||
| Information Retrieval | SCIDOCS (test) | 16 | Feb 26, 2026 | ||
| Theorem Proving | LeanDojo (random) | 16 | Feb 26, 2026 | ||
| Volumetric Image Registration | Abdominal Dataset 42 (test) | 16 | Feb 26, 2026 | ||
| Lung Segmentation | MIMIC (test) | 16 | Feb 26, 2026 | ||
| Multi-task Robotic Manipulation | RLBench | 16 | Feb 26, 2026 | ||
| Element Grounding | Multimodal-Mind2Web Cross-Task | 16 | Feb 26, 2026 | ||
| RTL code generation | RTLLM v2.0 (test) | 16 | Feb 26, 2026 | ||
| Hypergraph Node Classification | DBLP CA | 16 | May 12, 2026 | ||
| BeV Segmentation | nuScenes | 16 | Mar 16, 2026 | ||
| Constraint-following Instruction Evaluation | IFEval | 16 | Feb 26, 2026 | ||
| Robotic Manipulation | LIBERO five suites | 15 | Jul 9, 2026 | ||
| Compressed Video Perceptual Enhancement | JCT-VC standard (test) | 15 | Jul 9, 2026 | ||
| Change Detection | XiongAn (val) | 15 | Jul 9, 2026 | ||
| Change Detection | MT-Wuhan (val) | 15 | Jul 9, 2026 | ||
| Change Detection | VisNIR-HCD (val) | 15 | Jul 9, 2026 | ||
| Alzheimer's Disease Diagnosis | ADNI cohort (five-fold cross-validation) | 15 | Jul 9, 2026 | ||
| Classification | Full panel 40 datasets (24 real-world and 16 synthetic) | 15 | Jul 9, 2026 | ||
| Radiology Report Generation | CXPMRG-Bench 44 | 15 | Jul 9, 2026 | ||
| Line Segment Detection | Wireframe 462-image (val) | 15 | Jul 9, 2026 | ||
| Intrusion Detection | QUT-GOOSE ZSS 2023 (test) | 15 | Jul 8, 2026 |