Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1096 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Structure to Energy and Forces | OC20 S2EF 2M (val) | 26 | Feb 26, 2026 | ||
| Binary Segmentation | CVC-ClinicDB (test) | 26 | Feb 26, 2026 | ||
| Automatic Speech Recognition | Tuda-DE (test) | 26 | Feb 26, 2026 | ||
| Density Estimation | MINIBOONE d=43; N=36,488 (test) | 26 | Jun 30, 2026 | ||
| Deepfake Detection | FaceForensics++ (FF++) HQ (test) | 26 | Apr 15, 2026 | ||
| Multi-Concept Image Generation | 12-concept dataset | 26 | Feb 26, 2026 | ||
| 3D Multi-Object Tracking | KITTI car (val) | 26 | Feb 26, 2026 | ||
| Symbolic Reasoning | AQUA | 26 | Feb 26, 2026 | ||
| Fine-grained classification | Cars (test) | 26 | Jun 8, 2026 | ||
| ER Status Prediction | TCGA-BRCA internal cohort | 26 | Jun 23, 2026 | ||
| Point Cloud Completion | ShapeNet (test) | 26 | Mar 20, 2026 | ||
| SAR Object Detection | HRSID | 26 | Jun 1, 2026 | ||
| General Capability | 8 capability benchmarks Aggregate | 26 | Feb 26, 2026 | ||
| AI Agent Reasoning and Tool-use | GAIA | 26 | Jul 1, 2026 | ||
| Emotion Recognition | CAER-S | 26 | May 7, 2026 | ||
| Conversational Retrieval | TopiOCQA (test) | 26 | Feb 26, 2026 | ||
| Person Re-Identification | PRCC CC protocol (test) | 26 | Feb 26, 2026 | ||
| View Synthesis | Tanks-and-Temples | 26 | Mar 23, 2026 | ||
| Sex Classification | UKBioBank | 26 | Apr 7, 2026 | ||
| Speech Recognition | LibriSpeech (dev) | 26 | Jul 3, 2026 | ||
| Scene Classification | Scene Classification (test) | 25 | Jul 8, 2026 | ||
| Image Classification | UTKFace (test) | 25 | Jul 8, 2026 | ||
| Information Retrieval | Cross-Standard Control Association 1.0 (B) | 25 | Jul 8, 2026 | ||
| Information Retrieval | Control-to-Metric Association 1.0 (test A) | 25 | Jul 8, 2026 | ||
| Ancient-script OCR | Chronicles-OCR (test) | 25 | Jul 7, 2026 |