Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1130 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Video Question Answering | LiViBench 1.0 (test) | 25 | Feb 26, 2026 | ||
| Video-level Deepfake Detection | DFD | 25 | Mar 26, 2026 | ||
| Classification | MSTAR 8-shot | 25 | Feb 26, 2026 | ||
| Classification | MSTAR 4-shot | 25 | Feb 26, 2026 | ||
| Classification | MSTAR 2-shot | 25 | Feb 26, 2026 | ||
| 3D Shape Reconstruction | DTU (standard 15-scene split) | 25 | May 4, 2026 | ||
| Semantic Segmentation | COCO | 25 | Jun 15, 2026 | ||
| Scene Text Detection | ICDAR 2015 | 25 | Mar 27, 2026 | ||
| Brain Tumor Classification | Large-scale MRI dataset | 25 | Feb 26, 2026 | ||
| Hyperspectral Image Classification | Salinas (test) | 25 | Mar 24, 2026 | ||
| Image Classification | Food101 | 25 | Feb 27, 2026 | ||
| Facial Shadow Removal | UCB (test) | 25 | Feb 26, 2026 | ||
| Facial Shadow Removal | ASFW (test) | 25 | Feb 26, 2026 | ||
| Multimodal Understanding | MME-RealWorld Chinese | 25 | Mar 9, 2026 | ||
| Multimodal Understanding | MME-RealWorld English | 25 | Mar 9, 2026 | ||
| Vision-Language Perception | VL Perception Benchmarks TextVQA, POPE, Seed-Bench | 25 | Feb 26, 2026 | ||
| Vision-Language Reasoning | VL Reasoning Benchmarks MathVista, MVerse, MathVision, MMMU, R1-OV, MMStar | 25 | Feb 26, 2026 | ||
| Video Understanding | LongVideoBench (test) | 25 | Mar 5, 2026 | ||
| Visual Question Answering | BC-VL | 25 | Feb 26, 2026 | ||
| Footwear impression modeling | Forensic Footwear Images | 25 | Feb 26, 2026 | ||
| Vision-language tracking | TNL2K | 25 | Mar 4, 2026 | ||
| Real-world Super-Resolution | DIV2K (val) | 25 | May 12, 2026 | ||
| Comprehensive Emotion Assessment | EEmo-Bench | 25 | Feb 26, 2026 | ||
| Emotion Ranking | EEmo-Bench | 25 | Feb 26, 2026 | ||
| Visual Localization | 7Scenes Stairs | 25 | Apr 1, 2026 |