Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2298 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Link Prediction | CS | 16 | Feb 26, 2026 | ||
| Image Classification | 11 Datasets Average (New Class) | 16 | Feb 27, 2026 | ||
| Flattening | VR-Folding 1.0 (test) | 16 | Feb 26, 2026 | ||
| Video Recognition | UCF-101 (test) | 16 | Feb 26, 2026 | ||
| Factuality Evaluation | TruthfulQA latest (test) | 16 | Feb 26, 2026 | ||
| 3D Medical Image Segmentation | Left Atrium | 16 | Feb 26, 2026 | ||
| Entity Linking | FUNSD | 16 | Feb 26, 2026 | ||
| Co-speech motion generation | BEATX (test) | 16 | Feb 26, 2026 | ||
| Offline Model-Based Optimization | LogP | 16 | Feb 26, 2026 | ||
| Offline Model-Based Optimization | Branin | 16 | Feb 26, 2026 | ||
| Model-Based Optimization | Design-Bench | 16 | Feb 26, 2026 | ||
| Model-Based Optimization | Design-Bench 2022 (test) | 16 | Feb 26, 2026 | ||
| Task Predictive Performance | CelebA (test) | 16 | Feb 26, 2026 | ||
| Task Predictive Performance | CUB Incomp (test) | 16 | Feb 26, 2026 | ||
| Video Reconstruction | Webvid (val) | 16 | Feb 26, 2026 | ||
| Stereo Matching | KITTI 12 | 16 | May 13, 2026 | ||
| Offline Reinforcement Learning | D4RL Hopper v2 (test) | 16 | Feb 26, 2026 | ||
| Natural Language Understanding | ARC Challenge | 16 | May 21, 2026 | ||
| Confidence Alignment | TruthfulQA | 16 | Feb 26, 2026 | ||
| Image Retrieval | UKnow (test) | 16 | Feb 26, 2026 | ||
| Building Change Detection | SECOND | 16 | Feb 26, 2026 | ||
| Building Change Detection | WHU-CD 38 | 16 | Feb 26, 2026 | ||
| Face Verification | CFP-FP (val) | 16 | Feb 26, 2026 | ||
| Face Verification | CP-LFW (val) | 16 | Feb 26, 2026 | ||
| Face Verification | CA-LFW (val) | 16 | Feb 26, 2026 |