Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1854 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Partial Multi-Label Learning | recreation | 18 | Apr 13, 2026 | ||
| Retrieval | MMLongBench | 18 | Apr 13, 2026 | ||
| 3D Reconstruction | Simulation Data objects (test) | 18 | Apr 13, 2026 | ||
| Scene Understanding | NYU v2 | 18 | Apr 13, 2026 | ||
| Scene Understanding | CityScapes | 18 | Apr 13, 2026 | ||
| Agentic Tool Use | τ²-Bench Telecom | 18 | May 19, 2026 | ||
| Semiosis Quality Evaluation | HGI SemiosisArt | 18 | Apr 13, 2026 | ||
| Out-of-Distribution Detection | CIFAR10 to CIFAR10-OOD | 18 | Jun 23, 2026 | ||
| Long-context understanding | LongBench | 18 | Apr 13, 2026 | ||
| Top-k Recommendation | Amazon Beauty | 18 | Apr 13, 2026 | ||
| Logical Reasoning | K&K Logistics (test) | 18 | Apr 13, 2026 | ||
| Task Representation Accuracy | Task Vector Evaluation Suite Llama2-13B (test) | 18 | Apr 13, 2026 | ||
| Myopic choice evaluation | Complex generation settings | 18 | Apr 13, 2026 | ||
| Representation Injection Performance | Llama2-7B evaluation scenarios (test) | 18 | Apr 13, 2026 | ||
| Image Manipulation Localization | IMD 2020 | 18 | Jun 11, 2026 | ||
| General Performance Evaluation | O2M Benign Clinical Queries | 18 | Apr 13, 2026 | ||
| Safety Evaluation | O2M Harmful Clinical Queries | 18 | Apr 13, 2026 | ||
| S-box Generation | 8x8 S-box generation | 18 | Apr 13, 2026 | ||
| Video Temporal Grounding | TACoS | 18 | May 28, 2026 | ||
| Fact Verification | FEVER | 18 | Apr 10, 2026 | ||
| Long Video Understanding | MLVU (651s) | 18 | Apr 10, 2026 | ||
| Tabular Classification | URL (test) | 18 | Apr 10, 2026 | ||
| Feature Selection | Criteo, Avazu, AliCCP, ML-1M Aggregate | 18 | Apr 10, 2026 | ||
| Interactive Segmentation | GAMMA | 18 | Apr 10, 2026 | ||
| Interactive Segmentation | GS1 | 18 | Apr 10, 2026 |