Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 721 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Continual Learning | CIFAR-100 i-Blurry-50-10 (test) | 33 | Jun 11, 2026 | ||
| Chart Visual Question Answering | ChartBench 1.0 (test) | 33 | Jun 11, 2026 | ||
| Text-to-image generation | MJHQ-30K | 33 | Jun 9, 2026 | ||
| Mathematical Reasoning | AIME 25 | 33 | Jun 8, 2026 | ||
| Code Editing | CodeEditorBench | 33 | Jun 5, 2026 | ||
| Lane Departure Warning | 10 Drivers LDW Dataset (experimental) | 33 | Jun 5, 2026 | ||
| Dynamic Link Prediction | Contact transductive v1 (test) | 33 | Jun 4, 2026 | ||
| Dynamic Link Prediction | UN Vote transductive v1 (test) | 33 | Jun 4, 2026 | ||
| Dynamic Link Prediction | UN Trade transductive v1 (test) | 33 | Jun 4, 2026 | ||
| Dynamic Link Prediction | US Legis. transductive v1 (test) | 33 | Jun 4, 2026 | ||
| Dynamic Link Prediction | Can. Parl. transductive v1 (test) | 33 | Jun 4, 2026 | ||
| Dynamic Link Prediction | Flights transductive v1 (test) | 33 | Jun 4, 2026 | ||
| LLM Decoding | Long Context 128K | 33 | Jun 4, 2026 | ||
| Classification | TabZilla | 33 | Jun 4, 2026 | ||
| Classification | PFN | 33 | Jun 4, 2026 | ||
| Classification | OpenML-cc18 | 33 | Jun 4, 2026 | ||
| Classification | BCCO | 33 | Jun 4, 2026 | ||
| Face Verification | LFW headline settings | 33 | Jun 4, 2026 | ||
| Face Verification | BFW headline settings | 33 | Jun 4, 2026 | ||
| Face Verification | RFW headline settings | 33 | Jun 4, 2026 | ||
| Face Verification | LFW | 33 | Jun 4, 2026 | ||
| Face Verification | LFW headline | 33 | Jun 4, 2026 | ||
| Face Verification | RFW (test) | 33 | Jun 4, 2026 | ||
| Specification Alignment | SPECBENCH Average over scenarios | 33 | Jun 4, 2026 | ||
| Text Retrieval | MS-COCO 5-fold 1K (test) | 33 | Jun 4, 2026 |