Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2371 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mesh Quality Evaluation | saturn | 15 | Jun 5, 2026 | ||
| Mesh Quality Evaluation | roof image | 15 | Jun 5, 2026 | ||
| Mesh Quality Evaluation | lighthouse | 15 | Jun 5, 2026 | ||
| Image Denoising | Lena | 15 | Jun 5, 2026 | ||
| Image Denoising | Cameraman | 15 | Jun 5, 2026 | ||
| Image Denoising | Nimes | 15 | Jun 5, 2026 | ||
| Image Denoising | Remote2 | 15 | Jun 5, 2026 | ||
| Image Denoising | Remote 1 | 15 | Jun 5, 2026 | ||
| Audio-Language Model Evaluation | ALME | 15 | Jun 4, 2026 | ||
| Speech Emotion Recognition | SER | 15 | Jun 4, 2026 | ||
| Visual Speech Classification | VSC | 15 | Jun 4, 2026 | ||
| Figurative Language Detection | IRFL | 15 | Jun 4, 2026 | ||
| Node Classification | DGL dataset M (test) | 15 | Jun 4, 2026 | ||
| Floorplan Localization | LaMAR CAB cross-scene generalization | 15 | Jun 4, 2026 | ||
| Automatic Speech Recognition | SPGI (val) | 15 | Jun 4, 2026 | ||
| GUI Task Completion | AndroidWorld | 15 | Jun 30, 2026 | ||
| Reasoning Efficiency Evaluation | Qwen3 Reasoning Tasks Five-component aggregate Base | 15 | Jun 4, 2026 | ||
| Personalized News Categorization | LaMP-2N 1.0 (test) | 15 | Jun 4, 2026 | ||
| Personalized Citation Identification | LaMP-1 1.0 (test) | 15 | Jun 4, 2026 | ||
| Personalized Scholarly Title Generation | LaMP-5 | 15 | Jun 4, 2026 | ||
| Personalized News Headline Generation | LaMP-4 | 15 | Jun 4, 2026 | ||
| Personalized Product Rating | LaMP-3 | 15 | Jun 4, 2026 | ||
| Robust Policy Optimization | Robust Linear Quadratic Regulator (Robust LQR) adversarial normalized (test) | 15 | Jun 4, 2026 | ||
| Visual Document Retrieval | ViDoRe V1+V2 (test) | 15 | Jun 4, 2026 | ||
| Long-form Writing Evaluation | WritingBench In-domain (test) | 15 | Jun 4, 2026 |