Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 880 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | ImageNet Tiny | 30 | Apr 9, 2026 | ||
| Tabular Data Synthesis Fidelity | collins | 30 | Feb 26, 2026 | ||
| Logic reasoning | Causal Judgement | 30 | Feb 26, 2026 | ||
| Coreset Construction | Drug | 30 | Feb 26, 2026 | ||
| Coreset Construction | Crime | 30 | Feb 26, 2026 | ||
| Node Classification | Physics semi-supervised | 30 | Feb 26, 2026 | ||
| Node Classification | CS semi-supervised | 30 | Feb 26, 2026 | ||
| Mathematical reasoning | MultiArith Out of Distribution | 30 | Feb 26, 2026 | ||
| Anomaly Segmentation | VisA | 30 | Jul 2, 2026 | ||
| Continuous Control | MuJoCo HalfCheetah v4 | 30 | Jul 7, 2026 | ||
| General NLP Evaluation | Natural Language Benchmarks Aggregate | 30 | Feb 26, 2026 | ||
| Language | WSC | 30 | Feb 26, 2026 | ||
| Closed-loop Planning | nuPlan (val14) | 30 | Jul 7, 2026 | ||
| Question Answering | TruthfulQA zero-shot | 30 | Mar 4, 2026 | ||
| Gaussian color image denoising | Kodak24 (test) | 30 | Feb 26, 2026 | ||
| Image Classification | ImageNet OOD Variants | 30 | Jul 7, 2026 | ||
| Multi-object 3D Visual Grounding | Multi3DRefer | 30 | Apr 21, 2026 | ||
| Autonomous Driving | Bench2Drive 220 short segment scenarios | 30 | Mar 9, 2026 | ||
| Image Classification | SVHN | 30 | Feb 26, 2026 | ||
| Jailbreak Attack | MI (MaliciousInstructions) | 30 | Feb 26, 2026 | ||
| Jailbreak Attack | AdvBench AdvSub | 30 | Feb 26, 2026 | ||
| Anomaly Localization | MVTec AD few-shot | 30 | Feb 26, 2026 | ||
| Anomaly Detection | MVTec AD few-shot | 30 | Feb 26, 2026 | ||
| Spatial Understanding | RealWorldQA | 30 | Feb 26, 2026 | ||
| Question Answering | SocialIQA | 30 | Mar 13, 2026 |