Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1596 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Air Quality Prediction | KnowAir original (test) | 20 | Mar 19, 2026 | ||
| Knee MRI classification | MRNet | 20 | Mar 19, 2026 | ||
| Skin lesion recognition | Derm7pt | 20 | Mar 19, 2026 | ||
| Multimodal disease recognition | MMC-AMD | 20 | Mar 19, 2026 | ||
| LLM-as-a-Judge Evaluation | Average Across FB Bench, FLASK, Vic. Bench, MT Bench | 20 | Mar 19, 2026 | ||
| LLM-as-a-Judge Evaluation | Vicuna Benchmark | 20 | Mar 19, 2026 | ||
| Anomaly Detection | ATLAS | 20 | Mar 19, 2026 | ||
| Bundle Adjustment | BAL (Bundle Adjustment in the Large) (various scenes) | 20 | Mar 19, 2026 | ||
| Open-Domain QA | TriviaQA | 20 | Mar 19, 2026 | ||
| Text Reconstruction from Gradients | IMDB | 20 | Mar 18, 2026 | ||
| Text Reconstruction from Gradients | CoLA | 20 | Mar 18, 2026 | ||
| classification | SIENA | 20 | Jun 23, 2026 | ||
| classification | TUAB | 20 | Jun 23, 2026 | ||
| classification | HMC | 20 | Jun 23, 2026 | ||
| classification | SEED-V | 20 | Jun 23, 2026 | ||
| Mathematical Reasoning | Average Across all benchmarks | 20 | Mar 18, 2026 | ||
| Mathematical Reasoning | AIME 26 | 20 | Mar 18, 2026 | ||
| Mathematical Reasoning | AMC 23 | 20 | Mar 18, 2026 | ||
| Mathematical Reasoning | AIME 24 | 20 | Mar 18, 2026 | ||
| Mathematical Reasoning | Minerva | 20 | Mar 18, 2026 | ||
| Mathematical Reasoning | Olympiad | 20 | Mar 18, 2026 | ||
| Mathematical Reasoning | MATH-500 | 20 | Mar 18, 2026 | ||
| Long-video understanding | Video-Holmes (test) | 20 | Mar 18, 2026 | ||
| Semantic Segmentation | ADE20K (fine-tuning) | 20 | Mar 18, 2026 | ||
| Semantic Segmentation | Cityscapes fine-tuning | 20 | Mar 18, 2026 |