Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 182 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Personalization | CIFAR-100 (test) | 80 | Mar 4, 2026 | ||
| Model Inversion | CIFAR-10 | 80 | Mar 4, 2026 | ||
| Instruction Following | VicunaEval | 80 | Feb 27, 2026 | ||
| Medical Image Segmentation | Medical Image Segmentation Aggregate (Average of BUSI, BTMRI, ISIC, Kvasir-SEG, QaTa-COV19, and EUS) (test) | 80 | Feb 26, 2026 | ||
| Cumulative Reward | Qbert | 80 | Feb 26, 2026 | ||
| Adversarial Attack | Seaquest | 80 | Feb 26, 2026 | ||
| Adversarial Attack | Pong | 80 | Feb 26, 2026 | ||
| Cumulative Reward | Space Invaders | 80 | Feb 26, 2026 | ||
| IoT Attack Detection | IoTGeM Cross-Dataset (test) | 80 | Feb 26, 2026 | ||
| IoT Attack Detection | IoTGeM Session (test) | 80 | Feb 26, 2026 | ||
| IoT Attack Detection | IoTGeM (val) | 80 | Feb 26, 2026 | ||
| Interactive web-based shopping tasks | WebShop | 80 | Jun 25, 2026 | ||
| Robust Watermarking | COCO (test) | 80 | Feb 26, 2026 | ||
| Question Answering | TriviaQA (test) | 80 | May 19, 2026 | ||
| Concept Attribution | Pascal | 80 | Feb 26, 2026 | ||
| Mathematical Reasoning | Minerva | 80 | Mar 18, 2026 | ||
| Subtype diagnosis | CH dataset | 80 | Feb 26, 2026 | ||
| Benign-malignant classification | CH dataset | 80 | Feb 26, 2026 | ||
| Tumor screening | CH | 80 | Feb 26, 2026 | ||
| Societal Bias Ranking | U.S. Bureau of Labor Statistics (BLS) latest available (full set) | 80 | Feb 26, 2026 | ||
| Geometry Reconstruction | DTU | 80 | Feb 26, 2026 | ||
| Photometric Rendering | Replica (room0-2, office0-4) | 80 | Mar 31, 2026 | ||
| Classification | NWPU (test) | 80 | Feb 26, 2026 | ||
| Image Generation | Mind-Bench | 80 | Jun 26, 2026 | ||
| Text-driven Motion Generation | HumanML3D (test) | 80 | Jul 9, 2026 |