Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2729 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Speech-to-Portrait | VoxCeleb (test) | 14 | Mar 4, 2026 | ||
| Web Navigation Task Completion | Mind2Web (Cross-website 177) | 14 | Mar 4, 2026 | ||
| Hate Speech Analysis | PrideMM | 14 | Mar 4, 2026 | ||
| Reasoning | AIME 2024 | 14 | Mar 19, 2026 | ||
| Medical Dialogue | MAQuE | 14 | Mar 4, 2026 | ||
| Brain Functional Network Classification | ADHD-200 | 14 | Mar 4, 2026 | ||
| Generative Retrieval | Industrial Dataset | 14 | Mar 12, 2026 | ||
| Optical Character Recognition | TextOCR VL-ICL Bench | 14 | Mar 4, 2026 | ||
| Visual Reasoning | CLEVR VL-ICL Bench | 14 | Mar 4, 2026 | ||
| Object-Property Induction | VL-ICL Bench OP_IND | 14 | Mar 4, 2026 | ||
| Image Classification | Open-MI VL-ICL Bench | 14 | Mar 4, 2026 | ||
| Protein Fitness Prediction | ProteinGym (test) | 14 | Mar 4, 2026 | ||
| Software Engineering | SWE-Bench Pro 1.0 (test) | 14 | Mar 4, 2026 | ||
| Khmer Text Recognition | KHOB Document (evaluation) | 14 | Mar 4, 2026 | ||
| Agentic Text Synthesis | RAVEL | 14 | Mar 4, 2026 | ||
| Text Synthesis | C3EBENCH | 14 | Mar 4, 2026 | ||
| Collaborative 3D Object Detection | DAIR-V2X | 14 | Mar 4, 2026 | ||
| Collaborative 3D Object Detection | V2XSet | 14 | Mar 4, 2026 | ||
| Collaborative 3D Object Detection | V2XSim | 14 | Mar 4, 2026 | ||
| Time series forecasting | ETTh2 | 14 | Mar 26, 2026 | ||
| Video Classification | VGGSound-C severity level 5 | 14 | Mar 4, 2026 | ||
| Multi-hop QA | DROP (test) | 14 | Mar 4, 2026 | ||
| Fine-grained classification | Gastric endoscopic biopsy slides | 14 | Mar 4, 2026 | ||
| Coarse-grained classification | Gastric endoscopic biopsy slides | 14 | Mar 4, 2026 | ||
| Recommendation | Official Dataset | 14 | Mar 4, 2026 |