Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1228 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Jailbreak Detection | GoalFrameBench | 24 | Feb 26, 2026 | ||
| Faithfulness Evaluation | ImageNet (val) | 24 | Mar 17, 2026 | ||
| Bayesian network structure discovery | Child | 24 | Feb 26, 2026 | ||
| Bayesian network structure discovery | Cancer | 24 | Feb 26, 2026 | ||
| Bayesian network structure discovery | Asia | 24 | Feb 26, 2026 | ||
| Spatial-temporal calibration | TUM-VI | 24 | Feb 26, 2026 | ||
| Spatial-temporal calibration | EuRoC | 24 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (test) | 24 | Feb 26, 2026 | ||
| Person Re-identification | CCVID Configuration 1 (test) | 24 | Feb 26, 2026 | ||
| Link Prediction | WikiPeople | 24 | Mar 9, 2026 | ||
| Forward Visual Navigation (To End) | HM3D | 24 | Feb 26, 2026 | ||
| Any-Point Visual Navigation | HM3D | 24 | Feb 26, 2026 | ||
| Any-Point Visual Navigation | Gibson | 24 | Feb 26, 2026 | ||
| Recommendation | ML-100K (test) | 24 | Apr 7, 2026 | ||
| Multimodal Perception | MME perception-related tasks | 24 | Mar 9, 2026 | ||
| Random inpainting | AFHQ-Cat (test) | 24 | May 12, 2026 | ||
| Action Recognition | Drive&Act | 24 | Feb 26, 2026 | ||
| Eccentricity Prediction | Graph Property Prediction (test) | 24 | May 25, 2026 | ||
| SSSP Prediction | Graph Property Prediction (test) | 24 | May 25, 2026 | ||
| Diameter Prediction | Graph Property Prediction (test) | 24 | May 25, 2026 | ||
| Goal-conditioned Manipulation | OGBench puzzle-4x4-play | 24 | May 21, 2026 | ||
| Offline Reinforcement Learning | D4RL Antmaze umaze | 24 | May 29, 2026 | ||
| 5-way few-shot classification | tieredImageNet 5-way (meta-test) | 24 | Feb 26, 2026 | ||
| 5-way few-shot classification | miniImageNet 5-way (meta-test) | 24 | Feb 26, 2026 | ||
| Computer task execution | OSWorld (verified) | 24 | Feb 26, 2026 |