Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1859 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Backdoor Defense | SVHN (test) | 18 | Apr 7, 2026 | ||
| Discriminative Hallucination Evaluation | AMBER | 18 | Apr 21, 2026 | ||
| AI-generated image detection | AIGIBench | 18 | Jun 16, 2026 | ||
| Salient Object Detection | UserSOD (test) | 18 | Apr 7, 2026 | ||
| Functional Property Estimation | Synthetic Gamma Process Scenario B, sparsity {6, ..., 10} | 18 | Apr 7, 2026 | ||
| Functional Property Estimation | Synthetic Gamma Process Scenario B, sparsity {2, ..., 6} | 18 | Apr 7, 2026 | ||
| Sleep stage classification | ISRUC-S3 multivariate | 18 | Apr 7, 2026 | ||
| Activation Steering | DEBATEMIX | 18 | Apr 7, 2026 | ||
| LLM steering evaluation | ToneBank | 18 | Apr 7, 2026 | ||
| Trajectory Simulation | Geolife | 18 | Apr 7, 2026 | ||
| Hijacking detection | Tool-input hijacking detection dataset 20% (test) | 18 | Apr 7, 2026 | ||
| Video Understanding | VidHalluc | 18 | Apr 6, 2026 | ||
| Video Understanding | EventHallusion | 18 | Apr 6, 2026 | ||
| Structured Information Synthesis | WideSearch English | 18 | Apr 6, 2026 | ||
| Table Structure Recognition | BCDSTab | 18 | Apr 6, 2026 | ||
| Part Segmentation | ShapeNet In-Context 1.0 (test) | 18 | Apr 6, 2026 | ||
| Knowledge gap detection | MATH | 18 | Apr 6, 2026 | ||
| Knowledge gap detection | GSM8K | 18 | Apr 6, 2026 | ||
| Knowledge gap detection | MMLU | 18 | Apr 6, 2026 | ||
| Knowledge gap detection | HQA | 18 | Apr 6, 2026 | ||
| Knowledge gap detection | TQA | 18 | Apr 6, 2026 | ||
| Link Prediction | MKG-Y Equal split | 18 | Apr 6, 2026 | ||
| Link Prediction | MKG-Y (Higher split) | 18 | Apr 6, 2026 | ||
| Link Prediction | MKG-Y Entity split | 18 | Apr 6, 2026 | ||
| Link Prediction | MKG-W Equal split | 18 | Apr 6, 2026 |