Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2691 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| MEP-Lobby link discovery | Retweets | 14 | Apr 7, 2026 | ||
| Video Detection | VidProM | 14 | Apr 7, 2026 | ||
| Video Detection | VideoPhy | 14 | Apr 7, 2026 | ||
| Video Detection | EvalCrafter | 14 | Apr 7, 2026 | ||
| Video Detection | GenVideo | 14 | Apr 7, 2026 | ||
| AI-generated Video Detection | VidProM (test) | 14 | Apr 7, 2026 | ||
| Cooperative Navigation | Cooperative Navigation easy | 14 | Apr 7, 2026 | ||
| scRNA-seq imputation | human fetus cell atlas 25% low-biased missingness (MNAR) | 14 | Apr 7, 2026 | ||
| scRNA-seq imputation | Human heart cell atlas (50% MCAR) | 14 | Apr 7, 2026 | ||
| Semantic Segmentation | XSeg (test) | 14 | Apr 7, 2026 | ||
| End-to-end Autonomous Driving | NavHard (test) | 14 | Apr 7, 2026 | ||
| Phase Recovery | DIV2K Smooth phase (val) | 14 | Apr 7, 2026 | ||
| Phase Recovery | DIV2K Random phase (val) | 14 | Apr 7, 2026 | ||
| Phase Recovery | DIV2K Quadratic phase (val) | 14 | Apr 7, 2026 | ||
| Uncertainty Quantification | ARC-E | 14 | Apr 7, 2026 | ||
| Multi-modal Understanding | TVL Benchmark | 14 | Apr 7, 2026 | ||
| Spatial Reasoning | SPBench | 14 | Apr 7, 2026 | ||
| 2D binary segmentation | ColonDB | 14 | Apr 7, 2026 | ||
| Causal Evaluation | Lalonde Obs | 14 | Apr 7, 2026 | ||
| Causal Evaluation | Frugal DGP5 | 14 | Apr 7, 2026 | ||
| Causal Evaluation | Frugal DGP3 | 14 | Apr 7, 2026 | ||
| Causal Evaluation | Frugal DGP4 Simulator FrugalFlows Sim4(u) (synthetic) | 14 | Apr 7, 2026 | ||
| Causal Evaluation | Frugal DGP4 Simulator: FrugalParam Sim4(u) (synthetic) | 14 | Apr 7, 2026 | ||
| Causal Evaluation | LinearParam DGP1 Simulator Sim1 (synthetic) | 14 | Apr 7, 2026 | ||
| Question Answering | RepliQA | 14 | Apr 7, 2026 |