Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 877 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Dense Reconstruction | ETH3D (test) | 30 | Feb 27, 2026 | ||
| Spatial Reasoning | MindCube tiny (test) | 30 | Feb 26, 2026 | ||
| Automatic Speech Recognition | SPGISpeech | 30 | Jun 18, 2026 | ||
| HOMO prediction | QM9 | 30 | Feb 26, 2026 | ||
| Sexism Detection | EDOS SemEval Task 10 Task A 2023 (test) | 30 | Feb 26, 2026 | ||
| Image Generation | GenEval overall | 30 | Feb 26, 2026 | ||
| Misinformation Detection | COCO | 30 | Feb 26, 2026 | ||
| Tool Calling | Seal-Tools Single-Tool | 30 | Feb 26, 2026 | ||
| GUI Navigation | Mind2Web Cross-Task | 30 | Mar 30, 2026 | ||
| General Knowledge | MMLU-redux | 30 | Mar 4, 2026 | ||
| Human Mesh Reconstruction | EMDB 24 joints (test) | 30 | Mar 4, 2026 | ||
| Instruction Following | FollowRAG Instruction v1 (test) | 30 | Feb 26, 2026 | ||
| Instruction Following | FollowRAG Instruction | 30 | Feb 26, 2026 | ||
| Factuality Hallucination Evaluation | LongFact (test) | 30 | Feb 26, 2026 | ||
| Factuality Hallucination Evaluation | BioGEN (test) | 30 | Feb 26, 2026 | ||
| Factuality Hallucination | LongFact | 30 | Feb 26, 2026 | ||
| Factuality Hallucination | BioGEN | 30 | Feb 26, 2026 | ||
| Human-Object Interaction Detection | HICO-DET (UV) | 30 | Feb 26, 2026 | ||
| Regression | MoleculeNet LIPO | 30 | May 14, 2026 | ||
| Generalized Few-Shot Object Detection | MS-COCO 2017 (val) | 30 | Feb 27, 2026 | ||
| Anomaly Detection | Anomaly-ShapeNet | 30 | Jul 7, 2026 | ||
| Arithmetic Reasoning | GSM8K sampled subset n=200 (test) | 30 | Feb 26, 2026 | ||
| Novel-view synthesis | Co3D (test) | 30 | Feb 26, 2026 | ||
| Medical Image Classification | MedMNIST OrganS (test) | 30 | Feb 26, 2026 | ||
| 3D Appearance Preference Evaluation | Human Preference Evaluation Dataset Appearance | 30 | Feb 26, 2026 |